debug

A debugging workflow that loads a project's CANONIFY.md index and routes an error to the documented guidance for the relevant area. It accepts pasted errors, screenshots, or log-file references.

In plain words
What is it for?
Use it when a coding task includes an error, stack trace, screenshot, or log. It extracts paths, line numbers, error types, and named symbols to select the relevant guidance.
Why use it?
It puts the right project context in front of the debugger before diagnosis begins. Afterward, it helps capture newly discovered pitfalls so the same problem is less likely to recur.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/ewebdzine/canonify/debug
Any agent
npx skills add ewebdzine/canonify --skill debug
Clone the repo
git clone --depth 1 https://github.com/ewebdzine/canonify

Made for: Claude Code, Codex.

Per session 112 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,215 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 2d ago against content hash d24eecc7cfda, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

skills/debug/SKILL.md · 87 lines

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

  1. Load the index, set intent. Read CANONIFY.md (the manifest of one-line canon summaries). If the user typed /canonify:debug alone, acknowledge and wait for the error; if they included it, go on.

  2. 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.

  3. Route the error against the index. Walk the CANONIFY.md summaries 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.

  4. 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.

  5. 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-canon to tighten it) or /canonify:build never 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.

Read the full file on GitHub · 87 lines

Changes

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.

  1. 2d ago First seen · 87 lines · 112 tokens per session scan A d24eecc7cfda

Subscribe to this mod's changes

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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

vercel/next.js · 95 tokens

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…

openai/codex · 114 tokens

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…

openai/codex · 113 tokens

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…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 170 tokens