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/dixus/claudeframework/debugnpx skills add dixus/claudeframework --skill debuggit clone --depth 1 https://github.com/dixus/claudeframeworkWhat 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 | $0.00028 | $0.00476 |
| Opus 5 | $0.00014 | $0.00238 |
| Sonnet 5 | $0.00006 | $0.00095 |
| Haiku 4.5 | $0.00003 | $0.00048 |
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.
What it actually says
Diagnose and fix a specific failure. $ARGUMENTS is optional — pass an error message, test name, or file path to focus the investigation.
Goal
Identify the root cause and apply a minimal fix. Do not refactor surrounding code.
Steps
- Read CLAUDE.md — note the verify commands (typecheck, lint, test, build)
- Identify the failure:
- If $ARGUMENTS contains an error message or test name, use it as the starting point
- Otherwise run the full verify suite (typecheck → lint → tests) and capture the first failure
- Read the failing file(s) in full — understand the surrounding context before touching anything
- Form a hypothesis: one sentence describing the suspected root cause
- Validate the hypothesis before changing code:
- Check if the problem is in the implementation, the test, or the type definitions
- Look for similar patterns elsewhere in the codebase that work correctly — use Grep to find them
- If the hypothesis is wrong, revise it; do not apply fixes based on an unvalidated guess
- Apply the minimal fix — change only what the root cause demands
- Do not add defensive code, logging, or error handling unless directly required by the bug
- If the fix requires touching more than 3 files, pause and describe the situation to the user — the bug may be systemic
- Re-run the specific failing command to confirm the fix works
- Run the full verify suite to confirm no regressions were introduced
- If the verify suite still fails, return to step 4 with the new failure — do not apply a second fix on top of an incomplete first fix
- Report:
- Root cause (one sentence)
- Files changed and what changed
- Verify status before and after
- If the bug suggests a missing rule in CLAUDE.md or a context file, flag it — do not add it unilaterally
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 · 37 lines · 28 tokens per session scan A a0a9504bf4ec
debug is a skill published in the GitHub repository dixus/claudeframework (10 stars, last pushed 4mo ago), licensed MIT. It adds 28 tokens to every session and 476 once invoked, about $0.0001 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 2026-08-31.
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…