The repo had a `task check` structure gate and a 28-case shell test suite
that nothing ever ran. The only workflow auto-tagged every push to main, so
CI reported green having tested nothing — a gate that fails open, and the
reason `mathias/skills` shows up as repository-blocked in the estate backlog
classification.
release.yml becomes ci.yml with two jobs: `gate` runs check + test on every
push and PR; `tag` keeps the existing semver-from-trailer logic but declares
`needs: gate`, so a red check cannot ship a tag. The pull_request trigger
also gives `tbd_ship` a CI run to read on a branch head — without one it
fails closed and never merges (#22).
The tagger now pushes the manifest bump commit and the tag in a single
`git push`. Two pushes left a window where the gate ran `task check` on the
bump commit before the tag existed, and the manifest/tag parity assertion
would fail on a commit that was in fact correct.
tests/ci_gate_test.sh pins the wiring: PR trigger present, both tasks run,
tag needs gate, no second ungated workflow file.
Refs: #22
Bump-Type: minor
Wraps mathias/cad#14's `cad stuck` query surface: five-phase diagnostic
order (re-derive the worklist, read issue comments FIRST, then Actions job
logs, separate infrastructure fault from task outcome, decide-or-say
DECISION-NEEDED), read-only by Iron Law — no dispatch, no label writes, no
issue close. Every diagnosis cites a locator; every operator-only call
surfaces as a structured DECISION NEEDED block instead of being decided for
them.
Built after cad#14 passed its live-estate acceptance test (7 real findings,
locators verified) — the skill is the ritual around a query already proven
to produce actionable rows, not a checklist with no input.
Bump-Type: minor
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Found on flamingo during the first Mac install. ~/.config/crush/skills held
real directories from a pre-plugin install, and doctor said:
FAIL outside: ~/.config/crush/skills resolves to ~/.config/crush/skills,
outside the active checkout ~/.local/share/skills/skills
Naming a directory as its own resolution target is true and useless. Worse, it
pointed at the wrong fix: "outside" means a link into a foreign checkout, which
you repair by re-pointing the link. A real directory is repaired by moving it
aside and re-running install.sh — install.sh already refuses to delete it,
correctly, since it did not create it and cannot know what is in there.
Now reported as its own class, with the skill count so it is obvious whether
the directory holds a stale copy of the library or something unique that
belongs in the repo:
FAIL unmanaged: <dir> is a real directory, not a link into the checkout —
it holds N unmanaged skill(s); move it aside and re-run install.sh
The distinction matters because content in that directory reaches exactly one
harness and cannot receive new skills — the failure mode is silent divergence,
which is the same family as everything else this tool exists to catch.
Bump-Type: patch
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BeAp5LTscnz2W7Ubt4eJ6m
This skill is the third factory. Two repo templates were fixed when the
buildah->buildctl migration went through, and this one kept handing out
the broken step for weeks afterwards -- because it is what gets consulted
when adding CI to an EXISTING repo, which the templates never touch.
Pasting an implementation is the actual defect. The estate now has one
(mathias/infra ci-templates/build-image.sh) with byte-identical copies
held in place by a drift gate, so the skill teaches the four adoption
steps and the input list instead of a block to copy.
Step 1 of those four -- registering in adopters.txt -- is called out
explicitly, because a copy nobody registered works today and falls
silently behind on the next canonical change. That is the failure this
whole issue exists to end.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_011PL5XcG68SvQqz3vGVbWbf
This skill was the source of the buildah build step that infra#241 has
spent a sprint removing from nine repos: rootless buildah cannot run in
the containerized gitea-runner (drop ALL capabilities,
allowPrivilegeEscalation false, no OCI runtime), and the failure is
latent -- warm base-image layers hide it until the first cold pull.
Two templates were migrated for exactly this reason (stop new repos
inheriting the trap); this skill is the third factory and was still
handing out the broken pattern.
Also drops the `sudo k3s ctr` smoke test it recommended: written for the
Arch host runner, impossible in a pod (`sudo: command not found`). The
deploy job's rollout verification covers the same ground.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_011PL5XcG68SvQqz3vGVbWbf
Replaces the raw NodePort URLs with Tailscale Serve endpoints on koala:
brain https://koala.tail30472e.ts.net:8443/mcp -> 127.0.0.1:30330
infra https://koala.tail30472e.ts.net:8444/mcp -> 127.0.0.1:30342
Why this beats both alternatives that were tried:
The public d-ma.be path exits to Cloudflare and NPM to reach a k3s service on
the machine the session is running on, and Cloudflare rate-limits and
size-caps tool results — the original complaint. The raw NodePort path fixed
that but only worked from koala: every namespace carries default-deny-ingress
and an allow policy naming the traefik namespace, so kube-proxy's
KUBE-EXTERNAL-SERVICES chain RSTs external callers. Admitting tailnet clients
there would need externalTrafficPolicy: Local on each service plus an ipBlock
per policy, because the default Cluster policy SNATs the source and an ipBlock
can never match.
Serve sidesteps all of it. tailscaled terminates TLS with a genuine cert and
proxies over loopback, so the request reaches the NodePort from koala itself —
the case the NetworkPolicy already permits. No policy change, no
externalTrafficPolicy change, no firewall rule, no cert-manager, no DNS record.
Port-per-service rather than path-per-service: the mapping is 1:1 with no
prefix rewriting, so what the client requests and what the server sees cannot
desync.
Verified: 200 authenticated in 7.6ms from koala, and `claude mcp list` reports
Connected against the Serve URL. An earlier apparent OAuth resource-metadata
mismatch turned out to be an artifact of testing without an Authorization
header — with a valid bearer the client never enters OAuth discovery.
Client requirement: `tailscale set --accept-dns=true`. Confirmed on iguana that
100.100.100.100 resolves the MagicDNS name correctly while the system resolver
does not, so the name fails to resolve until Tailscale is accepted as a DNS
provider. Tracked in #24 as the Mac prerequisite. Note Serve matches on SNI, so
substituting the raw tailnet IP is not a workaround.
Bump-Type: minor
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BeAp5LTscnz2W7Ubt4eJ6m
Every MCP call from Claude Code was going out through claude.ai's connector
infrastructure, across the public internet, through Cloudflare and NPM on
piguard, back into koala's k3s ingress — to reach a service on the same
machine the session is running on. For brain that means a two-cloud round trip
to read /var/lib/supervisor/brain, a file on koala's local disk.
Cloudflare rate-limits and size-caps tool results on that path, which is the
actual user-facing symptom. Measured from koala:
brain koala:30330 200 in 6.8ms
infra koala:30342 200 in 3.6ms
brain public edge 200 in 27.7ms
infra starts working again as a side effect: its only fault was an SNI/cert
gap at the public edge (TLS "unrecognized name"), which the NodePort path does
not traverse. No NPM change needed for local use.
Note this is not a relocation of existing config. The mcpServers block that
lived in ~/.claude/settings.json was inert — Claude Code reads server
definitions from ~/.claude.json, project .mcp.json, plugins and connectors,
not from settings.json. Verified: a uniquely-named server placed there is
invisible to both `claude mcp list` and `claude mcp get`. So before the plugin
existed, koala had no direct path at all and every call went via Cloudflare by
construction. That also explains how a stale GITEA_MCP_TOKEN went unnoticed
for five days: nothing consumed it.
Safe to land now because koala is the only host with the plugin installed
(#24). The koala firewall must allow 30330/30342 on the Tailscale interface —
NOT on the LAN broadly, so tailnet membership stays the perimeter — before the
Macs get the plugin. Tracked as a prerequisite in #24. Measured today: those
ports are refused from iguana over both LAN and tailnet while :22 answers, so
the rule does not exist yet.
Bump-Type: minor
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BeAp5LTscnz2W7Ubt4eJ6m
Every gitea__* call from Claude Code on koala already resolves through the
claude.ai connector, not through this env-var-authenticated HTTP server. The
entry was a second path to the same service that nothing actually used.
That redundancy is exactly why it rotted unnoticed. GITEA_MCP_TOKEN on koala
resolves ~/.op-env -> op://HomeLab/GITEA_MCP_TOKEN, an item orphaned by the
2026-07-30 consolidation that moved gitea-mcp, agentsquad-serve and
crush-runner onto a single shared item in the AgentSecrets vault. The host
env-file was never migrated and cannot be: koala's 1Password service account
has no access to AgentSecrets, while onepassword-connect in-cluster maps both
vaults. So the host copy diverged and stayed diverged for five days.
The cluster was never affected — zero 401s from the pod CIDR in 30 days, every
rejection came from the gateway. Deleting the divergent copy beats maintaining
a second source of truth for a token this host does not need.
brain stays: it authenticates, and it is genuinely used from the plugin.
infra stays but is currently unreachable for an unrelated reason —
infra-mcp.d-ma.be fails TLS with "unrecognized name", an SNI/cert gap at the
NPM edge, tracked separately.
Bump-Type: patch
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BeAp5LTscnz2W7Ubt4eJ6m
The tagger searched the entire commit message for a bracketed marker as a
substring. The commit that introduced the manifest-bump step described that
marker in its own body — so the tagger read its own documentation as an
instruction and skipped the release. Run 15 reported success with no tag, no
manifest bump and no error. Same failure family as everything else in this
sweep: the wrong thing happened silently.
The rule is now a git trailer matched anchored to its own line, consistent
with Bump-Type, and it lives in bin/should-skip-release rather than untested
inside YAML. tests/release_skip_test.sh pins six cases, including the exact
regression: a message that spells the marker out in prose must still tag.
A marker you cannot mention without triggering is a footgun, not a mechanism.
Bump-Type: patch
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BeAp5LTscnz2W7Ubt4eJ6m
CI now writes the computed semver into .claude-plugin/plugin.json before
tagging, committed with [skip-release] so it does not re-trigger the tagger.
Claude Code gates plugin updates on that field: without the bump, installed
hosts never see a new tag no matter how many releases go out. `task check`
enforces manifest/tag equality so the two cannot silently diverge.
Docs rewritten around the two delivery paths, and the checkout location is now
stated as load-bearing rather than incidental: SKILLS_CHECKOUT_DIR defaults to
~/.local/share/skills because that is host-local and outside any synced
directory. The previous docs told you to clone into ~/dev, which on this fleet
is an iCloud folder shared by two Macs spanning two path roots — a git working
tree with concurrent writers, and absolute links that are broken on one side by
construction. That advice is what #23 is about; it is now inverted with the
reason attached.
Antigravity and Vibe removed from the docs along with their targets.
Bump-Type: patch
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BeAp5LTscnz2W7Ubt4eJ6m
Every failure this fleet actually hit was silent. 243 dangling symlinks were
invisible to git because **/.claude/skills/ is in the global gitignore. A
checkout 20 skills behind still resolved, so nothing complained. A loose
secret-hygiene.md loaded in no harness and errored in none. Two machines had
the library missing entirely. Exit status is the signal that was absent.
bin/doctor reports, with a non-zero exit:
- dangling links, anywhere under the harness dirs
- links that RESOLVE but land outside the active checkout — the dangerous
case, because it works while serving stale content
- skill-count mismatch between a harness and the checkout
- stray entries where <name>/SKILL.md was expected
- leftover per-skill Claude symlinks (plugin skills do not override
same-named user skills, so leftovers mean everything loads twice)
- divergence between the plugin copy and the copy the other harnesses link to
Wired as a SessionStart hook with --quiet, so a healthy host prints nothing and
a drifting one says so at the top of the next session. That beats a timer:
no launchd/systemd wiring, and it reaches every host that installs the plugin.
27ms on koala, no network, no git fetch.
Two design points found by the tests, both worth keeping:
- The canonical checkout is whatever ~/.agents/skills resolves to, NOT the
copy doctor runs from. As a plugin hook $0 lives in the plugin cache, which
is legitimately a second copy; judging harness links against it flagged
every one of them as "outside".
- "cd X/.." resolves ".." lexically against the link path and lands back in
~/.agents. Resolve the link first, then take the parent.
tests/doctor_test.sh drives seven fixtures through $HOME and $DOCTOR_CHECKOUT,
so no test touches the real host. Each asserts both the non-zero exit and that
the report names the fault — an exit-code-only assertion would pass while the
message said nothing useful.
Bump-Type: minor
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BeAp5LTscnz2W7Ubt4eJ6m
The plugin now carries the two hooks Mathias owns and the brain/gitea/infra
MCP server definitions, not just skills.
Why this matters more than tidiness: both hooks existed ONLY in koala's
~/.claude/, which is host-local and unsynced. flamingo and iguana have been
running with no secret-guard at all — that is the control which blocks the
decrypt-and-print shape behind the 2026-08-05 ntfy-token leak, the op-item-get
shape behind 2026-07-30, and the base64-bypass shape behind 2026-06-11. Its
absence on two of three machines is a security gap, not a config gap. Shipping
it in the plugin means installing the plugin installs the guard.
.mcp.json references tokens as ${BRAIN_MCP_TOKEN} / ${GITEA_MCP_TOKEN} only —
env indirection, never literal values, so the manifest is safe to commit.
tests/secret_guard_test.sh pins 14 cases. It asserts on
hookSpecificOutput.permissionDecision, NOT exit status: the guard always exits
0 by contract, so an exit-status assertion would pass vacuously while the guard
silently allowed everything. Each deny case names the incident that produced it.
gsd-* hooks are deliberately NOT migrated — GSD owns and updates those in place.
Bump-Type: minor
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BeAp5LTscnz2W7Ubt4eJ6m
Skills move to skills/<name>/SKILL.md and the repo gains both manifests, so
it is now a marketplace hosting exactly one plugin whose root is the repo
root (source: "."). Claude Code installs it from git; no symlinks involved.
Why: install.sh wired the library into every consuming repo as an ABSOLUTE
symlink to $CHECKOUT_DIR. The checkout moved three times, most recently when
local-dev@1966d5a dropped the embedded .skills/ copy, and nothing migrated
the links — 243 dangling links across 12 repos, hidden from git by the
**/.claude/skills/ ignore rule. Worse, ~/dev spans two path roots
(/Users/mathias on the iCloud-shared Macs, /home/mathias on koala), so an
absolute link stored there is broken on one side by construction. Re-running
the installer cannot fix that; only removing the mechanism can.
install.sh keeps the harnesses with no plugin system and drops from 42 links
per harness to one directory link, via the convergent ~/.agents/skills
convention that Pi and OpenCode both read:
~/.agents/skills -> $CHECKOUT_DIR/skills
~/.config/crush/skills -> ~/.agents/skills
~/.config/opencode/skills -> ~/.agents/skills
wire_claude_repo is deleted outright rather than gated behind a flag — on a
mixed-root fleet it cannot be made correct. Antigravity and Vibe targets go
too; both unused. CHECKOUT_DIR keeps its host-local default deliberately:
pointing it into ~/dev would put a git working tree inside iCloud with two
concurrent writers.
Taskfile drops five near-identical wiring loops (they had already drifted)
and delegates to install.sh. `task check` gains frontmatter validation, a
stray-root-entry gate, and manifest/tag version parity — the loose
secret-hygiene.md sat unloadable for months because nothing checked layout.
Verified: claude plugin validate . passes clean; a probe skill loaded as
skills:zzprobe through --plugin-dir; task check green at 42 skills.
Refs: #23
Bump-Type: minor
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BeAp5LTscnz2W7Ubt4eJ6m
Was a loose secret-hygiene.md at the root of ~/.claude/skills — not
dir/SKILL.md, so no harness ever loaded it. Promoted to a real skill so
it installs to Claude Code, Crush, Antigravity and Vibe alike.
Frontmatter description carries load-before triggers (kubectl exec/env,
whole-file SOPS decrypt, token rotation) so it fires ahead of the command
that would leak, not after.
Bump-Type: minor
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BeAp5LTscnz2W7Ubt4eJ6m
set -euo pipefail + `... | grep -iE '^Bump-Type:' | head -1 | awk ...`
inside `bump=$(...)`: when the last commit has no Bump-Type footer (the
normal default-to-patch case), grep exits 1 on no-match. Under
pipefail, that propagates as the whole pipeline's exit status even
though head/awk both succeed -- set -e then kills the script before it
ever reaches the case statement. Broke on every push since 2026-06-22
once a footer-less commit landed after the last one that happened to
carry a Bump-Type line. Appended `|| true` to swallow the expected
no-match case.
Verified this session: `task install` (and its sub-targets) wipe/skip the
per-skill symlinks (0/40 across all harnesses), while install.sh wires 40/40
reliably. Point the wiring docs at install.sh until the Taskfile bug is fixed.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The index still described local-dev's old wire-skills.sh / ~/dev/.skills
mechanism. This repo is now the canonical home; wiring is `task install`
(claude global+repo, crush, antigravity, vibe) or the curl|bash install.sh.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Ports the Vibe wiring from local-dev's wire-skills.sh so this repo's installer
covers all four harnesses. Vibe uses a flat layout — ~/.vibe/skills/<name>.md
symlinked to the skill's SKILL.md file (not the directory, unlike Claude/Crush/
Antigravity). Added to both `task install` and install.sh, idempotent.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Consolidating the divergence between this repo and local-dev's embedded
~/dev/.skills/ (the two had drifted; the 19 overlapping skills were byte-identical).
- Import the 17 skills that existed only in local-dev: discovery-framing,
stage-gate-review, web-shot, and the 14 superpowers-* skills. This repo is now
the superset / single source of truth.
- SKILLS_INDEX.md: add rows for the 17.
- install.sh + Taskfile.yml: git.d-ma.be host (was stale gitea.d-ma.be, which
broke the one-line curl|bash installer post-rename).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The two new skills shipped without the name/description frontmatter every
other skill carries, so harnesses surfaced them as a bare directory name
with no description to match against intent. Add frontmatter (body unchanged).
Bump-Type: patch
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The koala act_runner has labels [self-hosted, linux, amd64]. The
default ubuntu-latest label doesn't match, so the release workflow
silently produced zero runs on every push. Matches the convention
used by hyperguild + infra workflows.
Runner is offline at time of this commit — bring it up on koala via
the act_runner systemd unit before expecting tags to appear.
[skip-release]
Phase 2 of mathias/skills extraction. Adds two new per-tool wirers
alongside Claude Code:
- Crush — ~/.config/crush/skills/<name>/SKILL.md (charmbracelet/crush,
successor to opencode-ai/opencode which is archived)
- Antigravity — ~/.gemini/antigravity/skills/<name>/SKILL.md (Google
VS Code extension). Our SKILL.md frontmatter (name + description)
is already in the format Antigravity expects — no manifest
translation step needed.
Both wirers added to Taskfile.yml (install:crush + install:antigravity)
and install.sh (wire_crush + wire_antigravity). The aggregate `install`
target now calls all four targets (claude:global, claude:repo, crush,
antigravity). Idempotent symlinks, same shape as the Claude Code wirer.
Per-host env overrides documented in README: SKILLS_REF for tag pinning,
CRUSH_SKILLS_DIR + ANTIGRAVITY_SKILLS_DIR for non-default paths.
Skipped:
- opencode (opencode-ai/opencode): archived, succeeded by Crush; its
Custom Commands surface is user prompt templates, not system skills
- gitea-resident agents: consume via per-repo .claude/skills or brain
MCP, no special target needed
Bump-Type: minor
Phase 1 of mathias/skills extraction (infra#62 Track D — homelab
next-step plan addendum). Imports ~/dev/.skills/ verbatim (19 skill
dirs + SKILLS_INDEX.md) and adds the installation surface:
- Taskfile.yml — install / update / list / release / check targets
- install.sh — bootstrap installer for hosts without Task. Idempotent
symlink wirer; default checkout at ~/.local/share/skills/ on every
host; SKILLS_REF env var pins a tag (default: main).
- .gitea/workflows/release.yml — auto-tag every push to main by
Bump-Type footer (major/minor/patch, default patch). Skipped when
commit contains [skip-release].
- README — usage, versioning, contribution flow, secret-hygiene rule.
Phase 1 wires Claude Code only (~/.claude/skills/<name> global +
<repo>/.claude/skills/<name> per-repo). Phase 2 adds Crush, opencode,
antigravity, and gitea-resident agents (cobalt-dingo, agentsquad)
once their skill conventions are researched.
Public repo, markdown-only — no secrets, no client names. Verified
via pre-push grep before initial push.
[skip-release]
mathias
