fix(test): run the secret guard via its own shebang, not through sh

The suite piped hook input into `sh "$GUARD"`, which overrides the hook's
`#!/usr/bin/env bash` and tests an interpreter production never uses. Claude
Code executes the hook as a program.

On Debian /bin/sh is dash, which has no `set -o pipefail`, so the guard died
on line 23 before reading a byte of input:

    secret-guard.sh: 23: set: Illegal option -o pipefail
    secret_guard: 0 passed, 20 failed

while passing 20/20 on a host where /bin/sh happens to be bash. A security
gate that tests green and cannot start is the worst of both, and the test was
the only thing standing between those two states.

Found because baked-v16 added jq to the runner: this suite needs jq to build
its hook JSON, so it had been silently doing nothing in CI and started running
for the first time. Same shape as installing zip and immediately learning the
gitea backup check had never run -- a missing tool does not announce that it
is suppressing a whole suite.

Also asserts the hook is executable, since direct invocation depends on the
exec bit, and that assertion is what stops this regressing to `sh "$GUARD"`.

Checked the rest of the suite: every other `sh "$SUT"` targets a POSIX script,
which is correct. hooks/pre-task-ritual.sh is the other bash-shebang hook and
has no test at all -- filed separately rather than fixed here.

Bump-Type: patch

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "skills",
   "description": "Mathias's engineering skills library, plus the hooks and MCP servers that make it enforceable: TDD, clean code, debugging, specs, discovery, CI, and secret hygiene.",
-  "version": "0.17.1",
+  "version": "0.19.2",
   "author": {
     "name": "Mathias",
     "url": "https://git.d-ma.be/mathias"

.mcp.json

@@ -1,5 +1,5 @@
 {
-  "_comment": "Tailscale Serve on koala, not the public d-ma.be hostnames. The public path exits to Cloudflare and NPM to reach a k3s service on the same machine most sessions run on, which imposes rate limits and message-size caps on tool results. Serve terminates TLS with a real Tailscale cert and proxies to the NodePort over loopback, so traffic reaches the service from koala itself and satisfies the default-deny-ingress NetworkPolicy with no cluster change. Clients need 'tailscale set --accept-dns=true' for the MagicDNS name to resolve; see mathias/skills#24.",
+  "_comment": "Tailscale Serve on koala, not the public d-ma.be hostnames. The public path exits to Cloudflare and NPM to reach a k3s service on the same machine most sessions run on, which imposes rate limits and message-size caps on tool results. Serve terminates TLS with a real Tailscale cert and proxies to the NodePort over loopback, so traffic reaches the service from koala itself and satisfies the default-deny-ingress NetworkPolicy with no cluster change. Clients need 'tailscale set --accept-dns=true' for the MagicDNS name to resolve; see mathias/skills#24. Every ${VAR} below must be one ~/.op-env defines -- bin/check-mcp-env enforces that, because an undefined one sends an empty Authorization header and reports as 'requires authentication', which is indistinguishable from a revoked credential.",
   "mcpServers": {
     "brain": {
       "type": "http",
@@ -11,23 +11,24 @@
     "infra": {
       "type": "http",
       "url": "https://koala.tail30472e.ts.net:8444/mcp"
+    },
+    "gitea": {
+      "_comment": "gitea-mcp authenticates by PASS-THROUGH: the bearer is a Gitea PAT, which the server validates against Gitea and then acts as. So no dedicated MCP token is needed, and the AgentSecrets blocker that parked this entry (skills#32, #33) never applied to it -- DMABE_GITEA_API_TOKEN is op://HomeLab and already in the session environment. Verified 2026-09-07: initialize 200 (serverInfo gitea-mcp) and tools/list returns 41 tools. Two DIFFERENT PATs both authenticate while GITEA_MCP_TOKEN 401s, which is what proves this is pass-through validation and not a static-token comparison.",
+      "type": "http",
+      "url": "https://koala.tail30472e.ts.net:8446/mcp",
+      "headers": {
+        "Authorization": "Bearer ${DMABE_GITEA_API_TOKEN}"
+      }
     }
   },
   "_parked": {
-    "_reason": "cad and gitea-mcp are proxied, reachable and AUTHENTICATING: tailscale serve 8445 -> 127.0.0.1:31877 and 8446 -> 127.0.0.1:30340; an MCP initialize with the correct bearer returns 200 from both (serverInfo gitea-mcp 0.1.0, cad aed2aaf). They stay parked only because nothing puts those two tokens into the session environment. Both live in the 1Password AgentSecrets vault, and by deliberate design (infra#224, closed) no single identity on koala reads both vaults: koala-homelab is HomeLab-only and resolves ~/.op-env, koala-agentsecrets-write is AgentSecrets-only and lives in ~/.op-agent-write.env. Adding an AgentSecrets reference to ~/.op-env does NOT degrade gracefully -- `op run` fails wholesale and every other token, BRAIN_MCP_TOKEN included, goes unresolved with it. Enabling needs a read-scoped AgentSecrets identity in the session-env path; see mathias/skills#32, #33.",
+    "_reason": "cad is proxied, reachable and AUTHENTICATING: tailscale serve 8445 -> 127.0.0.1:31877, and an MCP initialize with the correct bearer returns 200 (serverInfo cad aed2aaf). It stays parked only because nothing puts CAD_MCP_TOKEN into the session environment. It lives in the 1Password AgentSecrets vault, and by deliberate design (infra#224, closed) no single identity on koala reads both vaults: koala-homelab is HomeLab-only and resolves ~/.op-env, koala-agentsecrets-write is AgentSecrets-only and lives in ~/.op-agent-write.env. Adding an AgentSecrets reference to ~/.op-env does NOT degrade gracefully -- `op run` fails wholesale and every other token, BRAIN_MCP_TOKEN included, goes unresolved with it. Enabling needs a read-scoped AgentSecrets identity in the session-env path; see mathias/skills#32, #33. gitea was parked here for the same stated reason and has been unparked: it needs no AgentSecrets token at all, because gitea-mcp is pass-through-authenticated.",
     "cad": {
       "type": "http",
       "url": "https://koala.tail30472e.ts.net:8445/mcp",
       "headers": {
         "Authorization": "Bearer ${CAD_MCP_TOKEN}"
       }
-    },
-    "gitea": {
-      "type": "http",
-      "url": "https://koala.tail30472e.ts.net:8446/mcp",
-      "headers": {
-        "Authorization": "Bearer ${GITEA_MCP_STATIC_TOKEN}"
-      }
     }
   }
 }

README.md

@@ -100,9 +100,11 @@ default to point into `~/dev`.
 | `AGENTS_SKILLS_DIR` | `$HOME/.agents/skills` |
 | `CRUSH_SKILLS_DIR` | `$HOME/.config/crush/skills` |
 | `OPENCODE_SKILLS_DIR` | `$HOME/.config/opencode/skills` |
+| `ANTIGRAVITY_SKILLS_JSON` | `$HOME/.gemini/config/skills.json` (registers `AGENTS_SKILLS_DIR` as a path entry; needs `jq`) |
 | `SKILLS_EXTRA_SOURCES` | unset (colon-separated extra source directories) |
 
-Antigravity and Mistral Vibe targets were removed — unused.
+The Mistral Vibe target was removed — unused. Antigravity's was removed for
+the same reason and re-added once it came back into use.
 
 ## Checking a host
 

Taskfile.yml

@@ -138,6 +138,26 @@ tasks:
           echo "ERROR: missing .claude-plugin/plugin.json" >&2; fail=1
         fi
 
+        # Every ${VAR} a live .mcp.json server interpolates must be one the
+        # session env-file defines. An undefined one is silent: the header
+        # goes out empty and the server reports "requires authentication",
+        # which reads as a revoked credential. Exit 2 means the check could
+        # not run (no jq, or no env-file — CI has neither); that is reported
+        # and not fatal, but it is never treated as a pass.
+        if [ -x "{{.TASKFILE_DIR}}/bin/check-mcp-env" ]; then
+          # `|| rc=$?` is load-bearing, not style. Task runs this block under
+          # `sh -e`, so a bare invocation exiting non-zero kills the shell
+          # before `case` is reached -- the tolerance below never ran, and the
+          # gate died with `exit status 2` on the commit that added it.
+          rc=0
+          "{{.TASKFILE_DIR}}/bin/check-mcp-env" "{{.TASKFILE_DIR}}/.mcp.json" "$HOME/.op-env" || rc=$?
+          case $rc in
+            0) ;;
+            2) echo "NOTE: MCP env wiring unverified on this host" >&2 ;;
+            *) fail=1 ;;
+          esac
+        fi
+
         if [ $fail -ne 0 ]; then
           echo "check FAILED" >&2; exit 1
         fi

bin/check-mcp-env

@@ -0,0 +1,99 @@
+#!/bin/sh
+# check-mcp-env — assert every variable a live MCP server interpolates is one
+# the session env-file actually defines.
+#
+# Why this is a gate and not a comment: the failure is silent. A header of
+# "Bearer ${FOO}" where FOO is undefined does not error -- it goes out empty,
+# the server answers 401, and Claude Code reports "requires authentication",
+# which reads exactly like a revoked credential. On 2026-09-07 that cost a
+# full investigation on koala before the credential turned out to be fine.
+#
+# Servers under `_parked` are exempt by design. Parked means "reachable, but
+# nothing puts its token in the environment yet" -- flagging those would
+# report the intended state as a fault.
+#
+# Usage:  check-mcp-env <mcp.json> <env-file>
+#
+# Exit 0  every live server's variables are defined
+#      1  at least one is not, named on stderr
+#      2  could not verify (bad usage, unreadable input, jq absent).
+#         Deliberately distinct from 0: an unverified config is not a clean
+#         one, and a gate that cannot run should say so rather than pass.
+
+set -u
+
+CONFIG=${1:-}
+ENVFILE=${2:-}
+
+if [ -z "$CONFIG" ] || [ -z "$ENVFILE" ]; then
+  echo "usage: check-mcp-env <mcp.json> <env-file>" >&2
+  exit 2
+fi
+
+if ! command -v jq >/dev/null 2>&1; then
+  echo "SKIP: jq not installed -- MCP env wiring unverified" >&2
+  exit 2
+fi
+
+if [ ! -f "$CONFIG" ]; then
+  echo "ERROR: no such config: $CONFIG" >&2
+  exit 2
+fi
+
+if [ ! -f "$ENVFILE" ]; then
+  # EXPECTED IN CI, and permanently so. The env-file holds live credentials, so
+  # it is not on the runner and must not be -- which means this check can only
+  # ever verify on a host that has one. infra#368 added jq to the runner image
+  # believing that would let CI verify; it removed the jq branch below and
+  # changed nothing else, because this branch is the binding one.
+  #
+  # Said plainly so nobody concludes CI covers this. It does not, it cannot,
+  # and putting ~/.op-env on the runner to make it would be trading a real
+  # secret for a green tick.
+  echo "ERROR: no such env-file: $ENVFILE -- cannot verify MCP variables" >&2
+  echo "       (expected in CI: this check only verifies on a host with ~/.op-env)" >&2
+  exit 2
+fi
+
+# Every "<server>\t<VAR>" pair a live server interpolates. `..` walks the whole
+# value, so a variable is found wherever it is placed, not only under headers.
+refs=$(jq -r '
+  .mcpServers // {}
+  | to_entries[]
+  | .key as $server
+  | (.value | .. | strings)
+  | select(test("\\$\\{"))
+  | [ scan("\\$\\{([A-Za-z_][A-Za-z0-9_]*)\\}")[] ]
+  | .[]
+  | "\($server)\t\(.)"
+' "$CONFIG" 2>/dev/null) || {
+  echo "ERROR: $CONFIG is not valid JSON -- MCP env wiring unverified" >&2
+  exit 2
+}
+
+if [ -z "$refs" ]; then
+  echo "check-mcp-env: no interpolated variables in live servers"
+  exit 0
+fi
+
+fail=0
+checked=0
+for pair in $(printf '%s\n' "$refs" | tr '\t' ':'); do
+  server=${pair%%:*}
+  var=${pair#*:}
+  checked=$((checked + 1))
+  if grep -qE "^[[:space:]]*(export[[:space:]]+)?$var=" "$ENVFILE"; then
+    continue
+  fi
+  printf 'ERROR: MCP server %s interpolates %s, which %s does not define.\n' \
+    "$server" "$var" "$ENVFILE" >&2
+  printf '       It will send an empty Authorization header and report as "requires authentication".\n' >&2
+  fail=1
+done
+
+if [ "$fail" -ne 0 ]; then
+  exit 1
+fi
+
+printf 'check-mcp-env: %d interpolated variable(s) across live MCP servers, all defined in %s\n' \
+  "$checked" "$ENVFILE"

install.sh

@@ -17,8 +17,8 @@
 #   /plugin install skills@mathias
 #
 # That path carries the hooks and MCP server definitions too, which symlinks
-# cannot. This script covers the harnesses with no plugin system: Crush, Pi
-# and OpenCode.
+# cannot. This script covers the harnesses with no plugin system: Crush, Pi,
+# OpenCode, and Antigravity.
 #
 # Wiring model — one managed directory, one link per harness:
 #
@@ -27,6 +27,13 @@
 #   ~/.config/crush/skills      -> ~/.agents/skills
 #   ~/.config/opencode/skills   -> ~/.agents/skills
 #
+# Antigravity has no symlink-directory discovery — it reads a path-entries
+# JSON instead (~/.gemini/config/skills.json:
+# {"entries":[{"path":"..."}]}). One entry points at ~/.agents/skills, so it
+# sees exactly the same surfaces-filtered, collision-resolved set every other
+# harness does. Requires jq; skipped with a warning if jq is unavailable —
+# every other target in this script stays dependency-free on purpose.
+#
 # ~/.agents/skills was itself a link to this checkout until #27. That encoded
 # an assumption nobody had stated — that this checkout is the ONLY source of
 # skills on the host — and on flamingo the only way to install this library
@@ -53,7 +60,12 @@ CHECKOUT_DIR="${SKILLS_CHECKOUT_DIR:-$HOME/.local/share/skills}"
 AGENTS_DIR="${AGENTS_SKILLS_DIR:-$HOME/.agents/skills}"
 CRUSH_DIR="${CRUSH_SKILLS_DIR:-$HOME/.config/crush/skills}"
 OPENCODE_DIR="${OPENCODE_SKILLS_DIR:-$HOME/.config/opencode/skills}"
+ANTIGRAVITY_SKILLS_JSON="${ANTIGRAVITY_SKILLS_JSON:-$HOME/.gemini/config/skills.json}"
 EXTRA_SOURCES="${SKILLS_EXTRA_SOURCES:-}"
+# Overridable so the jq-absent branch is testable on a host that has jq. That
+# branch is a contract, not a fallback: jq is optional here while every other
+# target in this script is dependency-free.
+JQ="${SKILLS_JQ:-jq}"
 # Recorded beside the managed directory rather than inside it: a stray file in
 # there would look like a skill to every harness reading the dir.
 SOURCES_MANIFEST="$(dirname "$AGENTS_DIR")/$(basename "$AGENTS_DIR")-sources"
@@ -213,6 +225,42 @@ link_dir() {
   log "linked $link → $target"
 }
 
+# wire_antigravity — register $AGENTS_DIR in Antigravity's skills.json.
+# Merges rather than overwrites: skills.json is a documented user-editable
+# config (json_configs.md), so a hand-added entry (e.g. a personal skills
+# dir) must survive a re-run untouched.
+wire_antigravity() {
+  if ! command -v "$JQ" >/dev/null 2>&1; then
+    log "Antigravity: jq not found — skipping (needed to merge $ANTIGRAVITY_SKILLS_JSON safely)"
+    return
+  fi
+
+  local existing already updated
+  mkdir -p "$(dirname "$ANTIGRAVITY_SKILLS_JSON")"
+
+  if [ -s "$ANTIGRAVITY_SKILLS_JSON" ]; then
+    existing="$(cat "$ANTIGRAVITY_SKILLS_JSON")"
+  else
+    existing='{}'
+  fi
+
+  already="$(printf '%s' "$existing" | "$JQ" --arg p "$AGENTS_DIR" \
+    '[.entries // [] | .[] | select(.path == $p)] | length' 2>/dev/null)" || {
+    log "Antigravity: $ANTIGRAVITY_SKILLS_JSON is not valid JSON — leaving it untouched"
+    return 1
+  }
+
+  if [ "$already" -gt 0 ]; then
+    log "Antigravity: $AGENTS_DIR already registered in $ANTIGRAVITY_SKILLS_JSON"
+    return
+  fi
+
+  updated="$(printf '%s' "$existing" | "$JQ" --arg p "$AGENTS_DIR" \
+    '.entries = ((.entries // []) + [{path: $p}])')"
+  printf '%s\n' "$updated" > "$ANTIGRAVITY_SKILLS_JSON"
+  log "Antigravity: registered $AGENTS_DIR in $ANTIGRAVITY_SKILLS_JSON"
+}
+
 main() {
   ensure_checkout
 
@@ -224,6 +272,7 @@ main() {
 
   link_dir "$CRUSH_DIR" "$AGENTS_DIR"
   link_dir "$OPENCODE_DIR" "$AGENTS_DIR"
+  wire_antigravity
 
   log "done — $LINKED_COUNT skill(s) linked from $(sources | wc -l | tr -d ' ') source(s), ref=$REF"
   log "Claude Code: install the plugin instead — /plugin marketplace add $REPO_URL"

skills/adr/SKILL.md

@@ -58,8 +58,8 @@ adr:           0004
 title:         <the decision, as a sentence — not "database choice">
 status:        proposed | accepted | superseded | amended
 date:          2026-08-29
-deciders:      <who accepted it, by name — or "pending: <name>" while proposed>
-supersedes:    <adr number, or ->
+deciders:      <who accepted it, by name — or "pending: <name>" (QUOTED) while proposed>
+supersedes:    <adr number, or null>
 ---
 
 # ADR-0004 — <same title>
@@ -97,6 +97,25 @@ the condition that fires a revisit. An ADR with no validation section is a prefe
 with a template around it.
 ```
 
+### The frontmatter must actually parse
+
+It exists to be machine-read, so a block that does not load is worse than no block at
+all: it drops that ADR silently out of every "what is still open?" query, while looking
+correct. Two shapes this template used to suggest are invalid YAML, and both were found
+live in the estate on 2026-09-05 — `openbanking-api` ADR-0001 and `infra` ADR-0019, each
+copied verbatim from here:
+
+| Wrong | Why | Right |
+|---|---|---|
+| `supersedes:    -` | a bare dash is a YAML *sequence entry*, not a string | `supersedes:    null` |
+| `deciders:      pending: Mathias` | the second, unquoted colon reads as a nested mapping | `deciders:      "pending: Mathias"` |
+
+Check before committing:
+
+```sh
+python3 -c "import yaml,sys;yaml.safe_load(open(sys.argv[1]).read().split('---')[1]);print('ok')" docs/adr/0004-*.md
+```
+
 ## Preserving a productive tension
 
 Some tradeoffs are not unresolved because nobody thought hard enough. They are

tests/check_tolerates_unverifiable_test.sh

@@ -0,0 +1,70 @@
+#!/bin/sh
+# `task check` must survive a check that reports "could not verify".
+#
+# The regression these exist for: bin/check-mcp-env exits 2 to mean "I could
+# not run — no jq, or no env-file", which the gate deliberately treats as a
+# reported NOTE rather than a failure. The Taskfile said exactly that:
+#
+#   "$DIR/check-mcp-env" "$DIR/.mcp.json" "$HOME/.op-env"
+#   case $? in 0) ;; 2) echo "NOTE: ..." ;; *) fail=1 ;; esac
+#
+# and it did not work. Task runs each cmds block under `sh -e`, so a bare
+# command exiting non-zero aborts the shell *before* `case $?` is ever
+# reached. The whole gate died with `exit status 2`. Locally the check found
+# jq and exited 0, so it went green; CI has neither jq nor ~/.op-env, so main
+# went red on the very commit that added it (skills run #57, 2026-09-07).
+#
+# A tolerated exit code that is only tolerated on the host where it never
+# fires is not tolerated at all. This pins the tolerance itself.
+#
+# No mocking: pointing HOME at an empty directory removes ~/.op-env, which is
+# exactly the condition CI runs under, so check-mcp-env genuinely exits 2.
+
+set -u
+
+ROOT=$(CDPATH= cd -- "$(dirname -- "$0")/.." && pwd)
+
+pass=0
+fail=0
+
+ok() { pass=$((pass + 1)); printf '  ok   %s\n' "$1"; }
+no() { fail=$((fail + 1)); printf '  FAIL %s\n' "$1"; }
+
+if ! command -v task >/dev/null 2>&1; then
+  printf '  SKIP: task not installed -- cannot exercise the gate\n'
+  exit 0
+fi
+
+TMP=$(mktemp -d)
+trap 'rm -rf "$TMP"' EXIT
+
+# Sanity: the precondition must actually hold, or the test proves nothing.
+# An empty HOME means no ~/.op-env, so check-mcp-env cannot verify anything.
+"$ROOT/bin/check-mcp-env" "$ROOT/.mcp.json" "$TMP/.op-env" >/dev/null 2>&1
+rc=$?
+if [ "$rc" -eq 2 ]; then
+  ok 'precondition: check-mcp-env exits 2 when the env-file is absent'
+else
+  no "precondition: expected check-mcp-env to exit 2, got $rc"
+fi
+
+# The assertion. `task check` must still pass, and must say why it could not
+# verify -- silence would mean the check was skipped rather than tolerated.
+out=$(HOME="$TMP" task --dir "$ROOT" check 2>&1)
+rc=$?
+
+if [ "$rc" -eq 0 ]; then
+  ok 'task check passes when MCP env wiring cannot be verified'
+else
+  no "task check exited $rc when check-mcp-env reported unverifiable"
+  printf '%s\n' "$out" | sed 's/^/       | /' | tail -8
+fi
+
+if printf '%s' "$out" | grep -q 'unverified'; then
+  ok 'the unverifiable check is reported, not silently skipped'
+else
+  no 'no NOTE reported -- an unverifiable check must never look like a pass'
+fi
+
+printf '  %d passed, %d failed\n' "$pass" "$fail"
+[ "$fail" -eq 0 ]

tests/install_test.sh

@@ -17,6 +17,7 @@ SUT="$ROOT/install.sh"
 
 pass=0
 fail=0
+skipped=0
 WORK=${TMPDIR:-/tmp}/install_test.$$
 
 if [ ! -f "$SUT" ]; then
@@ -55,6 +56,7 @@ run_install() {
     AGENTS_SKILLS_DIR="$_f/home/.agents/skills" \
     CRUSH_SKILLS_DIR="$_f/home/.config/crush/skills" \
     OPENCODE_SKILLS_DIR="$_f/home/.config/opencode/skills" \
+    ANTIGRAVITY_SKILLS_JSON="$_f/home/.gemini/config/skills.json" \
     SKILLS_EXTRA_SOURCES="$_extra" \
     bash "$SUT" 2>&1)
   rc=$?
@@ -156,6 +158,40 @@ else
   no 'configured sources are recorded for doctor' "$out"
 fi
 
+# --- Antigravity: jq is optional, so BOTH branches must be tested -----------
+# These three cases inherited whatever jq the host happened to have. koala has
+# it, the CI runner does not, so they passed locally and failed in CI — the
+# classic works-on-my-machine gate. install.sh treats jq as optional by design,
+# which means the skip is a contract and needs a test of its own.
+
+# run_install_nojq <fixture> — same as run_install, with the jq lookup pointed
+# at a binary that does not exist. Deterministic regardless of the host.
+run_install_nojq() {
+  _f=$1
+  _out=$(HOME="$_f/home" \
+    SKILLS_SKIP_FETCH=1 \
+    SKILLS_CHECKOUT_DIR="$_f/ck" \
+    AGENTS_SKILLS_DIR="$_f/home/.agents/skills" \
+    CRUSH_SKILLS_DIR="$_f/home/.config/crush/skills" \
+    OPENCODE_SKILLS_DIR="$_f/home/.config/opencode/skills" \
+    SKILLS_JQ="definitely-not-jq-$$" \
+    bash "$SUT" 2>&1)
+  rc=$?
+  printf '%s' "$_out"
+}
+
+f=$(new_fixture antigravity_nojq)
+out=$(run_install_nojq "$f")
+if [ -e "$f/home/.gemini/config/skills.json" ]; then
+  no 'without jq, no skills.json is written' "$out"
+elif ! printf '%s' "$out" | grep -qi 'jq not found'; then
+  no 'without jq, the skip is reported' "$out"
+elif [ ! -L "$f/home/.agents/skills/alpha" ]; then
+  no 'without jq, the other harnesses are still wired' "$out"
+else
+  ok 'without jq, Antigravity is skipped and the rest still wires'
+fi
+
 # --- 8. surfaces: the library link set is not "every skill" -----------------
 # claude.ai has no shell, no cluster and no checkout, so a chat-only skill
 # linked into Crush is a skill that can never fire, competing for selection
@@ -183,5 +219,59 @@ else
   no 'a source with no surfaces convention is linked as-is' "$out"
 fi
 
-printf '\ninstall: %d passed, %d failed\n' "$pass" "$fail"
+# --- 9-11. Antigravity's merge behaviour, only where jq exists ---------------
+# These three assert what jq DOES. install.sh treats jq as optional, so on a
+# host without it there is nothing to assert — and failing there is what turned
+# main red: they passed on koala (jq present) and failed on the runner (absent).
+# A skipped case is honest; a case that fails because the host lacks an optional
+# dependency is a false red, and false reds are how a suite stops being read.
+if ! command -v jq >/dev/null 2>&1; then
+  skipped=$((skipped + 3))
+  printf '  SKIP jq absent — Antigravity merge behaviour not covered on this host (3 cases)\n'
+else
+  # skills.json entries must point at $AGENTS_DIR — that carries the
+  # surfaces-filtering, collision handling and multi-source merge. Pointing at
+  # the checkout directly would give Antigravity a different skill set than
+  # every other harness.
+  f=$(new_fixture antigravity)
+  out=$(run_install "$f")
+  AG="$f/home/.gemini/config/skills.json"
+  if [ ! -f "$AG" ]; then
+    no 'Antigravity skills.json is created' "$out"
+  else
+    registered=$(jq -r --arg p "$f/home/.agents/skills" '[.entries[]? | select(.path == $p)] | length' "$AG")
+    if [ "$registered" = "1" ]; then
+      ok 'Antigravity registers the managed agents dir, not the raw checkout'
+    else
+      no 'Antigravity registers the managed agents dir, not the raw checkout' "$(cat "$AG")"
+    fi
+  fi
+
+  f=$(new_fixture antigravity_idempotent)
+  run_install "$f" >/dev/null
+  out=$(run_install "$f")
+  AG="$f/home/.gemini/config/skills.json"
+  count=$(jq '.entries | length' "$AG" 2>/dev/null || echo "?")
+  if [ "$count" = "1" ]; then
+    ok 'Antigravity wiring is idempotent (no duplicate entries)'
+  else
+    no 'Antigravity wiring is idempotent (no duplicate entries)' "entries=$count"$'\n'"$out"
+  fi
+
+  # A user may hand-edit skills.json to point at their own personal skills dir
+  # (json_configs.md documents this). Our merge must not clobber it.
+  f=$(new_fixture antigravity_preserve)
+  mkdir -p "$f/home/.gemini/config"
+  printf '{"entries":[{"path":"/Users/mathias/personal-skills"}]}' > "$f/home/.gemini/config/skills.json"
+  out=$(run_install "$f")
+  AG="$f/home/.gemini/config/skills.json"
+  personal=$(jq -r '[.entries[]? | select(.path == "/Users/mathias/personal-skills")] | length' "$AG" 2>/dev/null || echo 0)
+  if [ "$personal" = "1" ]; then
+    ok 'Antigravity wiring preserves pre-existing hand-authored entries'
+  else
+    no 'Antigravity wiring preserves pre-existing hand-authored entries' "$(cat "$AG")"$'\n'"$out"
+  fi
+fi
+
+printf '\ninstall: %d passed, %d failed, %d skipped\n' "$pass" "$fail" "$skipped"
 [ "$fail" -eq 0 ]

tests/mcp_config_test.sh

@@ -0,0 +1,118 @@
+#!/bin/sh
+# Tests for bin/check-mcp-env.
+#
+# The fault this gate exists for is silent, which is why it needs a gate at
+# all. An `.mcp.json` server whose Authorization header interpolates a
+# variable nothing in the session environment defines does not error: the
+# header goes out empty, the server answers 401, and Claude Code reports
+# "requires authentication". That is indistinguishable from a revoked or
+# expired credential, and on 2026-09-07 it cost a full investigation on koala
+# to establish that the credential was fine and the variable was simply never
+# set.
+#
+# So the property is: every ${VAR} a LIVE server interpolates must be a
+# variable the session env-file actually defines.
+#
+# The `_parked` block is deliberately exempt. Parked servers reference
+# variables nothing provides on purpose -- that is what parked means -- and a
+# gate that flagged them would be reporting the intended state as a fault.
+#
+# Fixtures drive the checker through argv, so no test touches the real host.
+
+set -u
+
+ROOT=$(CDPATH= cd -- "$(dirname -- "$0")/.." && pwd)
+CHECK="$ROOT/bin/check-mcp-env"
+
+pass=0
+fail=0
+WORK=${TMPDIR:-/tmp}/mcp_config_test.$$
+
+if [ ! -f "$CHECK" ]; then
+  printf 'FAIL: %s does not exist\n' "$CHECK"
+  exit 1
+fi
+
+cleanup() { rm -rf "$WORK"; }
+trap cleanup EXIT INT TERM
+mkdir -p "$WORK"
+
+if ! command -v jq >/dev/null 2>&1; then
+  printf 'SKIP: jq not installed -- bin/check-mcp-env cannot be exercised\n'
+  exit 0
+fi
+
+# ok <name> / bad <name> <detail>
+ok()  { pass=$((pass+1)); printf '  ok   %s\n' "$1"; }
+bad() { fail=$((fail+1)); printf '  FAIL %s  %s\n' "$1" "${2:-}"; }
+
+# run <mcp-json> <env-file> -> sets $rc and $out
+run() {
+  out=$("$CHECK" "$1" "$2" 2>&1); rc=$?
+}
+
+ENVFILE="$WORK/op-env"
+cat > "$ENVFILE" <<'ENVEOF'
+BRAIN_MCP_TOKEN=op://HomeLab/brain/token
+DMABE_GITEA_API_TOKEN=op://HomeLab/gitea/token
+ENVEOF
+
+# --- a live server whose variable IS defined ---------------------------------
+cat > "$WORK/good.json" <<'JSONEOF'
+{"mcpServers":{"brain":{"type":"http","url":"https://x/mcp",
+ "headers":{"Authorization":"Bearer ${BRAIN_MCP_TOKEN}"}}}}
+JSONEOF
+run "$WORK/good.json" "$ENVFILE"
+[ "$rc" -eq 0 ] && ok "defined variable passes" || bad "defined variable passes" "rc=$rc $out"
+
+# --- a live server whose variable is NOT defined ------------------------------
+# The exact shape that broke: the server looks correct and fails at runtime.
+cat > "$WORK/missing.json" <<'JSONEOF'
+{"mcpServers":{"gitea":{"type":"http","url":"https://x/mcp",
+ "headers":{"Authorization":"Bearer ${GITEA_MCP_STATIC_TOKEN}"}}}}
+JSONEOF
+run "$WORK/missing.json" "$ENVFILE"
+if [ "$rc" -ne 0 ]; then
+  case "$out" in
+    *gitea*GITEA_MCP_STATIC_TOKEN*) ok "undefined variable is flagged, naming server and variable" ;;
+    *) bad "undefined variable is flagged, naming server and variable" "report did not name both: $out" ;;
+  esac
+else
+  bad "undefined variable is flagged, naming server and variable" "rc=0"
+fi
+
+# --- a server with no headers at all (the `infra` shape) ----------------------
+# Unauthenticated by design. Nothing to resolve, so nothing to flag.
+cat > "$WORK/noauth.json" <<'JSONEOF'
+{"mcpServers":{"infra":{"type":"http","url":"https://x/mcp"}}}
+JSONEOF
+run "$WORK/noauth.json" "$ENVFILE"
+[ "$rc" -eq 0 ] && ok "header-less server is not flagged" || bad "header-less server is not flagged" "rc=$rc $out"
+
+# --- parked servers are exempt ------------------------------------------------
+cat > "$WORK/parked.json" <<'JSONEOF'
+{"mcpServers":{"brain":{"type":"http","url":"https://x/mcp",
+  "headers":{"Authorization":"Bearer ${BRAIN_MCP_TOKEN}"}}},
+ "_parked":{"_reason":"no identity provides these yet",
+  "cad":{"type":"http","url":"https://x/mcp",
+   "headers":{"Authorization":"Bearer ${CAD_MCP_TOKEN}"}}}}
+JSONEOF
+run "$WORK/parked.json" "$ENVFILE"
+if [ "$rc" -eq 0 ]; then
+  ok "parked server is exempt"
+else
+  bad "parked server is exempt" "rc=$rc $out"
+fi
+
+# --- malformed JSON must not pass silently ------------------------------------
+# A config the checker cannot read is an unverified config, not a clean one.
+printf '{"mcpServers":{' > "$WORK/broken.json"
+run "$WORK/broken.json" "$ENVFILE"
+[ "$rc" -ne 0 ] && ok "unparseable config does not report success" || bad "unparseable config does not report success" "rc=0"
+
+# --- a missing env-file is unverifiable, not clean ----------------------------
+run "$WORK/good.json" "$WORK/no-such-env"
+[ "$rc" -ne 0 ] && ok "missing env-file does not report success" || bad "missing env-file does not report success" "rc=0"
+
+printf '\n%s: %d passed, %d failed\n' "$(basename "$0")" "$pass" "$fail"
+[ "$fail" -eq 0 ]

tests/secret_guard_test.sh

@@ -24,7 +24,7 @@ decision_for() {
   _tool=${2:-Bash}
   jq -n --arg t "$_tool" --arg c "$_cmd" \
     '{tool_name: $t, tool_input: {command: $c}}' \
-    | sh "$GUARD" \
+    | "$GUARD" \
     | jq -r '.hookSpecificOutput.permissionDecision // "MISSING"'
 }
 
@@ -42,6 +42,20 @@ expect() {
   fi
 }
 
+# Invoked as a PROGRAM above, never as `sh "$GUARD"`. Claude Code executes the
+# hook directly, so its `#!/usr/bin/env bash` shebang decides the interpreter;
+# piping it into `sh` overrides that and tests something production never runs.
+#
+# It is not academic. On Debian /bin/sh is dash, which has no `set -o
+# pipefail`, so the guard died on line 23 before reading a byte of input and
+# every deny case returned empty -- 20 of 20 assertions failed in CI while
+# passing on a host where /bin/sh happens to be bash. A security gate that
+# tests green and cannot start is the worst of both.
+if [ ! -x "$GUARD" ]; then
+  printf 'FAIL: %s is not executable -- it must run via its own shebang\n' "$GUARD"
+  exit 1
+fi
+
 if [ ! -f "$GUARD" ]; then
   printf 'FAIL: %s does not exist\n' "$GUARD"
   exit 1