grill-canon
Skill1 starsChanged 38 days agoApache-2.0View on GitHub
Grill CURRENT and accepted ADRs for staleness, contradiction, and missing decisions. Use when asked to audit the brain, grill the canon, or check whether docs are still truth.
In this repository9 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .cursor/rules/agent-comms.mdcCursor rule
- .cursor/rules/project.mdcCursor rule
- brain-protocolSkill
- consistency-auditSkill
- grillingSkill
- grill-meSkill
- snowshoe-scratchSkill
- snowshoeSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 16
Ask only what is unsettled *in the docs*.
- Distinctive: line 25
Use grilling format: numbered frontier questions, recommended answer, then wait if a decision is required.
- Distinctive: line 31
Do not "fix" product direction by editing truth during the audit unless asked
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Grill the canon
Subject is the brain, not a new feature pitch.
Read
START_HERE → CURRENT → ROADMAP → EXPERIMENTS → accepted ADRs. Open evidence/notes only where CURRENT cites them.
Frontier (typical first round)
Ask only what is unsettled in the docs. Recommended checks:
- Does CURRENT still match every
status: acceptedADR? - Are experiments or evidence treated as if they were truth?
- Behavior or positioning with no ADR?
- Stale
updated:/ superseded ADR still implied by CURRENT? - Invented metrics, users, or competitors (forbidden)?
- Scope creep into non-goals (chat hell, AI review, multiplayer KG, agent HITL)?
Use grilling format: numbered frontier questions, recommended answer, then wait if a decision is required. Pure facts you can verify in-repo: report as findings, do not quiz the user.
Output
- Findings (canon vs evidence vs silence)
- Proposed patches (CURRENT and/or ADRs) — apply only after the user confirms
- Do not "fix" product direction by editing truth during the audit unless asked
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

