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/doidor/agentrig/log-gotchanpx skills add doidor/agentrig --skill log-gotchagit clone --depth 1 https://github.com/doidor/agentrigWhat 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 | $0.00040 | $0.00857 |
| Opus 5 | $0.00020 | $0.00428 |
| Sonnet 5 | $0.00008 | $0.00171 |
| Haiku 4.5 | $0.00004 | $0.00086 |
Grade A, and why
log-gotcha 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.
How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
log-gotcha (principle 8)
Every mistake is a prompt bug. The wiki is how the harness learns: every entry there is one agent-turn the next agent skips because they already know what you discovered. Logging is part of the task, not a separate "good-to-have" step.
When to log
You should log a gotcha if any of these apply to what you just did:
- A test, framework, or runtime did something surprising (e.g.
divide(1, 0)returnsInfinitynot throws;node --test some-dirresolves the dir as a module;console.logafterprocess.exitsilently truncates piped output). - A library default bit you (silent overwrite, surprising coercion, hidden API contract).
- An AGENTS.md rule wasn't loud enough — you almost violated it, or did, until you caught yourself.
- A non-obvious cross-file dependency that someone touching one file would miss.
- A flaky test, an environment-specific assumption, a build-cache surprise.
Do not log taste opinions, style preferences, or things that are already in CONTRIBUTING.md.
How to log
- Check the wiki first. Run
ls .agents/wiki/andgrep -ri "<keyword>" .agents/wiki/for the most natural keywords. If an existing entry covers it, SHARPEN that entry instead of adding a near-duplicate (the wiki README has a strict admission test on duplication). - Pick a topic file. Either an existing one (e.g.
troubleshooting.md) or create.agents/wiki/<topic>.mdif the area is new (e.g.node-test-runner.md,html-templates.md). Topic names are kebab-case nouns. - Write a stub entry using the template below. Keep it terse — 5 lines max.
- Commit it as part of your fix's diff. Wiki entries are not "after-the-fact paperwork" — they go in the SAME commit/PR as the fix that revealed them, so reviewers can see them.
Entry template
### <short noun-phrase title>
- **Symptom:** what went wrong / how it showed up
- **Cause:** the real root cause (not the symptom)
- **Fix:** the change you made (or wider remediation)
- **Prevention:** one-line rule that would have spared you this discovery
- **Discovered:** <date> in <scenario or task id>
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 · 69 lines · 40 tokens per session scan A de432c5255d8
log-gotcha is a skill published in the GitHub repository doidor/agentrig (5 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 857 once invoked, about $0.0002 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…