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 agentmods add skills/ewebdzine/canonify/commitnpx skills add ewebdzine/canonify --skill commitgit clone --depth 1 https://github.com/ewebdzine/canonifyWhat 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 | $0.00072 | $0.01526 |
| Opus 5 | $0.00036 | $0.00763 |
| Sonnet 5 | $0.00014 | $0.00305 |
| Haiku 4.5 | $0.00007 | $0.00153 |
Grade A, and why
commit 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 2d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Canonify: Commit
The Commit gate of Canonify - the last of three lifecycle gates, all routing through CANONIFY.md. Same routing logic as /canonify:build, opposite direction:
- Build (
/canonify:build): task description -> matchCANONIFY.mdsummary lines -> load implicated docs -> write code following the canonical patterns. - Commit (this skill,
/canonify:commit): diff -> match the same summary lines -> load the same implicated docs -> check the diff against the rules in those docs.
This skill does pattern adherence only. It does NOT check scope creep, intent, or "did we build the right thing." It checks "did we follow the canonical patterns the docs document."
How to run
-
Refresh the routing map. Read
CANONIFY.mdat the repo root. Note the one-line summaries for every doc - those are the routing signals. -
Get the diff. In parallel:
git diff(unstaged changes)git diff --cached(staged changes)git status(to see new files not yet diffed)
Combine into a working set of touched files and the actual line changes.
-
Walk every CANONIFY.md summary line and ask whether the diff touches that area. This is the inverse of the plan-time read: the summaries are the complete checklist of doc-covered patterns; iterate over them so nothing slips by.
For each doc-summary line in
CANONIFY.md:- Read the one-paragraph summary describing what that doc covers.
- Evaluate against the diff: does the diff touch anything described in that summary? Consider:
- File paths touched (a new file under a path the summary names clearly implicates that doc).
- Types, methods, or facades named in the change (a call to a facade the summary describes implicates that doc even if the file lives elsewhere).
- Patterns introduced (a new class implementing an interface a summary covers implicates that doc regardless of folder).
- File-type or surface rules (any file of a type a summary governs implicates that doc).
- Cross-cutting rules (any change in a language or area a project-wide rules doc covers implicates that doc).
- If yes -> mark that doc as implicated. If no -> record it as skipped with a one-line reason.
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.
- 2d ago First seen · 120 lines · 72 tokens per session scan A ebad13cf2f59
commit is a skill published in the GitHub repository ewebdzine/canonify (23 stars, last pushed 2mo ago), licensed MIT. It adds 72 tokens to every session and 1,526 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…