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/debugnpx skills add ewebdzine/canonify --skill debuggit 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 | $0.00112 | $0.01215 |
| Opus 5 | $0.00056 | $0.00607 |
| Sonnet 5 | $0.00022 | $0.00243 |
| Haiku 4.5 | $0.00011 | $0.00121 |
Grade A, and why
debug 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debug - route an error to its canon, then feed the fix back
Canonify's reactive gate - the twin of /canonify:build. Build routes a task forward to its
canons; Debug routes a failure to the canon for the area it lives in, so Claude diagnoses with the
documented patterns and gotchas already in context instead of grepping the project cold. Then, once
the bug is fixed, it closes the loop: the lesson goes back into the canon so the same class of bug
cannot recur.
Canonify does not do the debugging. This gate front-loads the right context and, at the end, points you at the capture command - the diagnosis and fix in between are normal work.
How to run
-
Load the index, set intent. Read
CANONIFY.md(the manifest of one-line canon summaries). If the user typed/canonify:debugalone, acknowledge and wait for the error; if they included it, go on. -
Take the error in. Accept any form: pasted text, a screenshot (read it via vision and transcribe the message + stack), or a referenced log file (read it). Pull out the routing signal: the file paths + line numbers in the stack frames, the exception / error type, and the symbols / methods named.
-
Route the error against the index. Walk the
CANONIFY.mdsummaries and ask which canon's area the error falls in. A stack trace is a precise routing signal - it names exact files and symbols, a stronger match than a prose task. If a canon's area matches, load it in full, paying special attention to its Gotchas section (the known footguns for that area). If nothing matches, proceed on breadth alone and say so - do not shoehorn the error into an unrelated canon. -
Debug normally. With the right canon (and its gotchas) in context, find the cause and propose/apply the fix in the user's usual flow. This step is ordinary debugging - the gate's value is the context it loaded around it.
-
Close the loop - suggest, never write. Judge whether the bug carries a durable, reusable lesson (a footgun worth documenting), then point at the right command:
- a reusable footgun + a canon was loaded -> "worth a gotcha in
<canon>- run/canonify:update-canon", and state the rule/gotcha you would add. - a reusable footgun + no canon covers the area -> "this area is undocumented - run
/canonify:create-canon". - the loaded canon ALREADY warns about this -> surface it: the gotcha exists but the bug
happened anyway, so either it needs to be sharper (
/canonify:update-canonto tighten it) or/canonify:buildnever loaded that canon for the original task. This is feedback on the canon, not a new entry. - a one-off slip with no general lesson -> say so and suggest nothing. Don't nag.
- a reusable footgun + a canon was loaded -> "worth a gotcha in
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 · 87 lines · 112 tokens per session scan A d24eecc7cfda
debug is a skill published in the GitHub repository ewebdzine/canonify (23 stars, last pushed 2mo ago), licensed MIT. It adds 112 tokens to every session and 1,215 once invoked, about $0.0006 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…