Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Abilityai/abilities --skill add-canon-lintgit clone --depth 1 https://github.com/Abilityai/abilitiesWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/abilityai/abilities/add-canon-lint)<a href="https://agentmods.dev/skills/abilityai/abilities/add-canon-lint"><img src="https://agentmods.dev/badge/skills/abilityai/abilities/add-canon-lint.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00167 | $0.03014 |
| Opus 5 | $0.00084 | $0.01507 |
| Sonnet 5 | $0.00033 | $0.00603 |
| Haiku 4.5 | $0.00017 | $0.00301 |
Grade A, and why
add-canon-lint scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add Canon Lint
ℹ️ First, set expectations: before anything else, print one short line with this skill's version and its most recent change — the top entry of
metadata.changelogabove — e.g.add-canon-lint vX.Y — recent: <summary>. Then proceed.
Make the fleet's canon repo mechanically self-consistent: a deterministic linter — plain Python, zero dependencies, zero LLM — that runs on every push and enforces the two-zone folder schema (facts.yaml structured claims + enveloped prose in docs/), catches cross-folder fact conflicts, stale canon, ownership violations, and unreachable docs before they become drift disputes.
Division of labor (the design): the linter on every push = internal consistency — grammar, ownership, one-home-per-key, staleness bounds. Each agent's scheduled /canon-reconcile = external truth — does the fact still match reality? The linter deliberately never judges content; reconcile deliberately never re-derives what the linter already proved.
Where the gates sit (own-folder writes are direct pushes, so CI alone cannot block them):
| Gate | When | Blocks? |
|---|---|---|
/canon-publish local lint (add-canon ≥1.4 runtime skills) |
before every push | yes — the real gate for agent writes |
.github/workflows/canon-lint.yml |
every push + PR | red X; backstop for human edits and drift |
| Required status check (optional, Step 6) | PRs to protected branches | yes — for protocols/ + cross-folder PRs |
This skill targets the canon repo, not an agent — run it once per fleet, from the orchestrator, any enrolled agent, or inside the canon repo itself. /add-canon installs the layer; this installs its law.
Process
Step 1: Preflight — locate the canon repo
Resolve the target, first match wins:
- Run from an enrolled agent —
template.yamlhasx-canon:→ target is the clone atclone_path(defaultcanon/); if the clone is missing, self-heal it exactly as/canon-publishStep 1 does (auth-aware). - Run inside the canon repo —
agents/directory andCONVENTIONS.mdpresent → target is the current directory. - Neither — ask for the canon repo ref (
github:Org/repo→ clone to a temp dir, or a local path).
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 186 lines · 167 tokens per session scan A f00ae0a2d9de
add-canon-lint is a skill published in the GitHub repository Abilityai/abilities (11 stars, last pushed 20d ago), licensed MIT. It adds 167 tokens to every session and 3,014 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…