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/anatomia-dev/anatomia/troubleshootingnpx skills add anatomia-dev/anatomia --skill troubleshootinggit clone --depth 1 https://github.com/anatomia-dev/anatomiaWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/anatomia-dev/anatomia/troubleshooting)<a href="https://agentmods.dev/skills/anatomia-dev/anatomia/troubleshooting"><img src="https://agentmods.dev/badge/skills/anatomia-dev/anatomia/troubleshooting.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00031 | $0.01131 |
| Opus 5 | $0.00015 | $0.00566 |
| Sonnet 5 | $0.00006 | $0.00226 |
| Haiku 4.5 | $0.00003 | $0.00113 |
Grade C, and why
troubleshooting scanned grade C with 1 finding 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 3d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
**Re-init doesn't show new template content.** CLAUDE.md, AGENTS.md, and agent definitions use merge-not-overwrite — existing files are preserved. To see fresh template output after changing templates, delete the existin How it starts
The opening of the file, as written. The whole thing — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Troubleshooting
Detected
Common Issues
- TypeScript reports "possibly null" or "possibly undefined" after a type guard, but only in async functions — the guard works in sync code — Type narrowing does not persist across
awaitboundaries because the variable could be reassigned between suspension points. Re-narrow after eachawait:if (!x) throwbefore theawait, thenif (!x) throwagain after. - Object literal type is widened to
stringinstead of the literal value, or array type isstring[]instead of a tuple — Addas constto the declaration:const x = { type: "success" } as constgives{ readonly type: "success" }instead of{ type: string }. For arrays:const arr = ["a", "b"] as constgivesreadonly ["a", "b"]instead ofstring[]. - "ERR_REQUIRE_ESM" when importing an ESM-only package, or "SyntaxError: Cannot use import statement in a module" — ESM-only packages (like
chalkv5+,execav6+,node-fetchv3+) cannot berequire()'d. Either: (1) switch your project to ESM ("type": "module"in package.json), (2) use dynamicimport()for the ESM package, or (3) pin an older CJS-compatible version. - Process crashes with "UnhandledPromiseRejection" — an async function throws but nothing catches it — Ensure every Promise chain has a
.catch()or is inside atry/catchin anasyncfunction. For fire-and-forget promises, add.catch(err => logger.error(err)). Check for missingawaiton async calls — without it, the rejection is unhandled. Prevention: Addprocess.on("unhandledRejection", handler)as a safety net, but fix the root cause — unhandled rejections indicate a code bug. - Tests hang indefinitely in CI or when run from scripts — process never exits — Vitest defaults to watch mode in interactive terminals. Pass
--runflag to run tests once and exit:vitest runinstead ofvitest. In CI, Vitest auto-detects non-interactive environments, but scripts piping output may still trigger watch mode. Prevention: Always usevitest runin CI scripts and non-interactive contexts. - Tests pass individually but fail when run together — mock from one test bleeds into another — Call
vi.restoreAllMocks()inafterEachor setmockReset: true/restoreAllMocks: trueinvitest.config.ts. Module mocks (vi.mock()) persist across tests in the same file — usevi.unmock()or restructure to avoid shared module-level mocks.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago First seen · 35 lines · 31 tokens per session scan C 9a576391c54f
troubleshooting is a skill published in the GitHub repository anatomia-dev/anatomia (32 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 1,131 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
agent-browser
Drive a real browser to inspect or interact with a web page or app — navigate, take screenshots, read console and network, fill simple forms — for verification tasks, not unattended automation.
requesting-code-review
Pre-commit review: security scan, quality gates, auto-fix.
workflow
Use when a task is too large for turn-by-turn orchestration and should run through the big-task workflow lane: system-wide changes, large migrations, repo-wide audits, high-confidence verification, or tasks explicitly asking to run a workflow. Claude Code uses native dynamic workflows; Codex, OpenCode, and Grok use…
verification-strategy
Thorough verification of completed work before declaring done.
gsd-verifier
Verifies phase goal achievement through goal-backward analysis. Checks codebase delivers what phase promised, not just that tasks completed.
gsd-integration-checker
Verifies that integrations work correctly by checking endpoints, responses, and data flow. Spawned by /gsd:complete-milestone orchestrator.