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/mlopscommunity/coding-agents-conference-skills/agent-maintained-docsnpx skills add mlopscommunity/Coding-Agents-Conference-skills --skill agent-maintained-docsgit clone --depth 1 https://github.com/mlopscommunity/Coding-Agents-Conference-skillsWrote 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/mlopscommunity/coding-agents-conference-skills/agent-maintained-docs)<a href="https://agentmods.dev/skills/mlopscommunity/coding-agents-conference-skills/agent-maintained-docs"><img src="https://agentmods.dev/badge/skills/mlopscommunity/coding-agents-conference-skills/agent-maintained-docs.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 | $0.00046 | $0.02517 |
| Opus 5 | $0.00023 | $0.01259 |
| Sonnet 5 | $0.00009 | $0.00503 |
| Haiku 4.5 | $0.00005 | $0.00252 |
Grade A, and why
agent-maintained-docs 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 5d 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 — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent-Maintained Documentation
Overview
A technique for keeping codebase documentation perpetually current by embedding it directly in source files and enforcing updates through commit-time hooks. Every file gets a header comment describing its purpose, every folder gets a README, and a validation hook rejects commits where code changed but docs did not.
Core principle: Documentation is a codebase navigation tool for agents. When an agent greps for "authentication" or "payment processing," file header comments and folder READMEs surface the right files instantly. Agents will reliably maintain these docs if you enforce it -- humans will not.
Dependency: A git hooks mechanism (husky, lefthook, pre-commit, or a bare .git/hooks/pre-commit script).
When to Use
- When creating any new file in the project
- When modifying a file's purpose, exports, or public interface
- When adding a new folder or reorganizing the project structure
- When onboarding agents to an existing codebase that lacks navigability
- When multiple agents (or agent sessions) work across the same repo
When NOT to Use
- Trivial internal implementation changes that do not alter a file's purpose or interface
- Auto-generated files (build output, lockfiles, compiled assets)
- Third-party vendored code you do not own
Common Mistakes
| Mistake | Why it's wrong |
|---|---|
| Writing docs only in a top-level wiki or docs site | Agents navigate by grepping the source tree. Docs outside the source tree are invisible to file-level search. |
| Trusting humans to keep file headers updated | They won't. Rob: "Agents maintain docs reliably if enforced; humans don't." Enforce with hooks or it decays within weeks. |
| Putting implementation details in the header comment | Header comments describe what and why, not how. Implementation details change constantly and create noisy diffs. |
| Skipping the commit-time validation hook | Without enforcement, the practice erodes immediately. The hook is what makes this sustainable. |
| Writing vague one-word descriptions like "Utils" or "Helpers" | These are useless for search. A header should tell an agent exactly what functionality lives in this file so grep returns meaningful hits. |
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.
- 5d ago First seen · 258 lines · 46 tokens per session scan A 5375b8aef154
agent-maintained-docs is a skill published in the GitHub repository mlopscommunity/Coding-Agents-Conference-skills (37 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 46 tokens to every session and 2,517 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 2026-08-30.
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…