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/cookys/autopilot/debugnpx skills add cookys/autopilot --skill debuggit clone --depth 1 https://github.com/cookys/autopilotWhat 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 | $0.00088 | $0.01174 |
| Opus 5 | $0.00044 | $0.00587 |
| Sonnet 5 | $0.00018 | $0.00235 |
| Haiku 4.5 | $0.00009 | $0.00117 |
Grade B, and why
debug scanned grade B with 2 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
!`cat .claude/debug-config.md 2>/dev/null || echo "No project-specific debug config found. Use generic evidence collection below."` Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| **Connectivity** | Timeout, refused, DNS failure | curl, netcat, ping, tcpdump, browser Network tab | How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evidence-First Debugging
Routing overlap? If this intent better matches a sibling skill, redirect per references/routing-tiebreaks.md (prefer single-bug diagnosis over baseline test design).
Coexistence with Superpowers
This skill is autopilot's standalone fallback for debugging methodology. If the superpowers plugin is installed, you may prefer superpowers:systematic-debugging — both work; .claude/dispatch-config.md's ## Debugging chain controls which one orchestrator skills (ceo-agent / finish-flow / quality-pipeline) dispatch.
Differences worth knowing:
- autopilot:debug is evidence-first (tool → log → code) with explicit Three Red Lines integration and
debug-config.mdproject context injection. Stricter discipline; prescriptive ordering. - superpowers:systematic-debugging is more general-purpose with broader hypothesis-driven framing. Less prescriptive, broader applicability.
!cat .claude/debug-config.md 2>/dev/null || echo "No project-specific debug config found. Use generic evidence collection below."
Core Principle
1. Tool-collected evidence -> profiler, logs, EXPLAIN, debugger, DevTools
2. Log analysis -> correlate with tool findings
3. Source code analysis -> informed by evidence from 1 + 2
Never guess from code alone. Always collect evidence first.
Relationship with Profiling
| Skill | When to Use |
|---|---|
| debug | Correctness: crashes, bugs, logic errors, data corruption, connectivity |
| profiling | Performance: slow queries, high memory, CPU spikes, latency |
If unsure, start with debug. If evidence points to a performance root cause, switch to profiling.
Debug Cycle
- Reproduce the issue reliably
- Collect evidence with appropriate tools
- Form hypothesis based on evidence
- Verify hypothesis (don't assume)
- Fix root cause (not symptoms)
- Verify fix with same tool + same test
- Record in knowledge base if non-trivial (invoke learn skill)
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 · 96 lines · 88 tokens per session scan B b1c284fb965c
debug is a skill published in the GitHub repository cookys/autopilot (11 stars, last pushed 2d ago), licensed MIT. It adds 88 tokens to every session and 1,174 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). 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…