mathias
1d140ec525
Implements #5's decision. The hard part was #37's, not #5's: which skills need an escalation rule? A hardcoded list rots, sniffing the prose for "does this write anything" is unfalsifiable, and a frontmatter flag is the option #5 rejected wearing a hat. So there is no acting set. Every skill answers the question, and a read-only one answers it in a line. That turns an absence into a claim someone can disagree with, which is the whole point — "this skill never hands back" is a design decision worth stating, and today it was indistinguishable from nobody having thought about it. Eleven written here, all advisory or read-only, where the honest answer is short and the value is in being specific rather than generic. `cognitive-load` stops when the metric disagrees with the people reading the code, because that is evidence about the metric. `test-design` stops when the tests are fine and the design under test is what makes them awkward. `code-review` stops when the diff is big enough that a review would be a skim, and says so rather than producing confident coverage of a fraction. The remaining thirty are the acting set — writes, dispatches, credentials, releases — and each needs a rule someone thought about rather than a rote paragraph, so they sit in bin/escalation-pending.txt. That list only shrinks, and it is self-cleaning: a listed skill that HAS a section fails the gate, so an exemption cannot outlive its reason. Mutation-verified both ways. Six test cases including the stale-entry case, because an exemption for a skill that no longer exists is how a gate quietly stops covering something. Refs #37, closes the mechanism half Bump-Type: minor
3.2 KiB
name, surfaces, summary, use_when, description
| name | surfaces | summary | use_when | description | ||
|---|---|---|---|---|---|---|
| telos-load |
|
Load TELOS intention substrate at session start | Starting any koala session; before architectural decisions; CAD pipeline entry | Load TELOS — the intention substrate (problems, goals, strategies, status) — into a session at start so every decision traces to a goal. Use when starting any koala session, before architectural decisions, or as the CAD pipeline entry point ("load TELOS", "what are we optimizing toward?"). |
telos-load
Load TELOS — the intention substrate — into a session so every decision can be traced back to a goal, and every goal to a problem.
Use when: starting any session on koala (Claude Code, Crush, Antigravity), or whenever a session needs to know what we are optimizing toward. If you find yourself making architectural decisions without knowing the active goals, load TELOS first.
Do not skip: a session without TELOS context is flying blind. It may produce technically correct output that is strategically wrong.
What TELOS is
TELOS is a wing in brain (wiki/telos/decisions/) containing 9 files: PROBLEMS, MISSION, GOALS, CHALLENGES, PROJECTS, STRATEGIES, BELIEFS, WRONG, STATUS. Together they answer: what are we working against, what are we trying to build, and how do we approach the work?
Full aggregate: wiki/telos/decisions/principal-telos.md
Loading TELOS by harness
Claude Code (per-project CLAUDE.md)
Add to the project CLAUDE.md or ~/.claude/CLAUDE.md:
Intention context (TELOS)
At session start, call brain_context with wing=telos and limit=8. Fallback if brain MCP unavailable: wiki/telos/decisions/principal-telos.md in the brain repo.
The global ~/.claude/CLAUDE.md was wired on koala on 2026-06-16.
Crush
Location on koala: ~/.config/crush/CRUSH.md (auto-loaded via global_context_paths). Add:
Intention context (TELOS)
At session start: query brain MCP with wing=telos, limit=8. If brain MCP unavailable: read wiki/telos/decisions/principal-telos.md
Antigravity
Add @brain_context wing=telos directive at top of system instructions.
Fallback — no brain MCP
cat ~/dev/AI/brain/wiki/telos/decisions/principal-telos.md
Or @-import in CLAUDE.md: @~/dev/AI/brain/wiki/telos/decisions/principal-telos.md
Verification
brain_query wing=telos limit=3 → Expected: PROBLEMS, MISSION, GOALS returned
brain_answer "what am I currently optimizing toward?" → Expected: non-empty, telos-sourced → If empty: use brain_query wing=telos (known fallback, brain#11 fixed)
When TELOS is stale
Update STATUS.md via: brain_write wing=telos hall=decisions filename=STATUS
Relationship to CAD
TELOS is the intention layer in the CAD pipeline. Every Gitea issue created in a CAD session should trace to a TELOS GOAL. Every GOAL traces to a PROBLEM.
Traceability chain: PROBLEM → GOAL → SPEC → TICKET → IMPL → TEST
Escalation
Read-only. Loads intention context; changes nothing.
Stop and hand back when: the brain is unreachable or returns nothing for the wing. Working from a remembered TELOS is the failure this skill exists to prevent — say the load failed rather than reconstructing it from memory.