agentleFS
Sign inStart free
bestdeejay-designbestdeejay-design/agent-skills/skills/canon/SKILL.md

canon

Skill6 starsChanged 3 months agoMITView on GitHub

Orchestrator for the Chronos Pantheon — runs agent presets (minimal/standard/full), aggregates reports, validates cross-references between L1-L3 (contracts → product → engineering). Use when: "run full audit", "chronos full", "cross-reference validation", "canon".

9 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Do not use as a standalone documentation analyzer.

    line 73

“Common” is measured: kept by at least 6 in 10 of the 6 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Canon — Orchestrator

Runs Chronos agent presets, aggregates reports, validates cross-references between L1-L3.

Presets

PresetAgentsDescription
minimalCensorDuplicates + broken links only
standardCensor + Dewey + CanonCheck + classify + cross-ref
fullAll 5 agentsComplete Pantheon

What it does

  1. Receives preset (minimal/standard/full)
  2. Determines required agents
  3. Executes agents in sequence
  4. Aggregates findings into unified report
  5. Validates L1→L2→L3 cross-references (contracts match docs)

Usage

# Via Chronos orchestrator
chronos --path . --preset full

# Direct invocation
python -m chronos.agents.canon --path . --preset full

Cross-Reference Validation

Canon checks consistency between levels:

  • L1→L2: OpenAPI endpoints documented in PRD/FEATURES
  • L2→L3: Architecture decisions trace to PRD requirements
  • L3→L1: ADRs reference contract versions

Output Format

[info] preset: full
[info] agents_run: censor, dewey, veles, canon
[warning] cross_ref: GET /users in openapi.yaml (v2.1) but PRD.md shows v2.0
[critical] cross_ref: ADR-005 references deprecated endpoint removed in v2.1

Triggers

  • run full audit / full audit
  • chronos full / chronos --preset full
  • cross-reference validation / cross ref check
  • canon

Integration

Loaded by Chronos as part of standard and full presets. Canon is both an agent and the preset orchestrator.

Boundaries

  • Do not use as a standalone documentation analyzer; use the focused chronos, censor, dewey, or veles skill when only one audit is needed.

Inputs and decision rules

Input is a repository path and one preset. Start with minimal when the user asks for a narrow check; use standard for a PR and full for a release audit. Never infer that a missing document is a defect without showing the detected project level and the configured requirement.

Output gate

A run is complete only when the selected agents, issue count, preset, project path, and output format are visible in the report. For CI, use JSON and --fail-on; inspect at least one finding's file, category, severity, and fix. A zero-issue report is not proof that unscanned file types or unavailable external systems were checked.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free