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/codejunkie99/agentic-stack/debug-investigatornpx skills add codejunkie99/agentic-stack --skill debug-investigatorgit clone --depth 1 https://github.com/codejunkie99/agentic-stackWhat 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 | $0.00003 | $0.00371 |
| Opus 5 | $0.00002 | $0.00186 |
| Sonnet 5 | $0.00001 | $0.00074 |
| Haiku 4.5 | $0.00000 | $0.00037 |
Grade A, and why
debug-investigator 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
Debug Investigator — systematic, not vibes-based
Follow this loop every time. Jumping straight to "fix" without reproducing is how false fixes ship.
The loop
- Reproduce. Get a deterministic failure. If you can't reproduce, you can't fix.
- Isolate. Bisect the problem space: narrow inputs, narrow code paths, narrow time windows.
- Hypothesize. Form one explicit hypothesis. Write it in
memory/working/WORKSPACE.mdunder "Active hypotheses". - Test the hypothesis. A single change that proves or disproves it — no shotgun fixes.
- Verify. After the fix, re-run the repro. If the bug is gone, the repro is your new regression test.
What to log
- Each hypothesis that was wrong (high importance; these compound into domain knowledge).
- The actual root cause and why it wasn't obvious.
Anti-patterns
- "It works now, not sure why" — keep investigating.
- Adding
try/exceptto silence an error without understanding it. - Changing five things at once and claiming one of them fixed it.
Self-rewrite hook
If the same class of bug appears 3+ times (timezone bugs, race conditions,
off-by-one), promote a lesson to LESSONS.md and update this skill with
a domain-specific sub-procedure.
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 · 40 lines · 3 tokens per session scan A 0f4911b60cde
debug-investigator is a skill published in the GitHub repository codejunkie99/agentic-stack (2,241 stars, last pushed 26d ago), licensed Apache-2.0. It adds 3 tokens to every session and 371 once invoked, about $0.0000 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…