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/marin-community/marin/fix-docsnpx skills add marin-community/marin --skill fix-docsgit clone --depth 1 https://github.com/marin-community/marinWrote 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/marin-community/marin/fix-docs)<a href="https://agentmods.dev/skills/marin-community/marin/fix-docs"><img src="https://agentmods.dev/badge/skills/marin-community/marin/fix-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 | $0.00027 | $0.00499 |
| Opus 5 | $0.00014 | $0.00249 |
| Sonnet 5 | $0.00005 | $0.00100 |
| Haiku 4.5 | $0.00003 | $0.00050 |
Grade A, and why
fix-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 4d 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
Fix the markdown docs within lib/iris, lib/zephyr and lib/fray so they
comply with the principles below. Do NOT touch docs outside those directories.
Output: dispatch sub-agents that (1) parse the code and docs and (2) make the documentation changes locally. Commit the changes into a single local commit, inform the user, and summarize what changed. Never push without explicit user approval.
Principles
- Agents are the primary consumers of documentation. Coding agents write
most Marin code; humans use agents as "documentation brokers". Segregate docs
by audience:
- Human docs live in
docs/— high-level, "getting started", concise. - Agent docs live in the directory tree next to the code they describe — token-efficient.
- Human docs live in
- Agentic docs follow standards so agents know where to look. Entry points:
**/AGENTS.md— targeted agent guidance for the subtree, plus a recursive ToC/index of subtree content.**/OPS.md— field guide for gathering telemetry, running commands, and debugging the systems in the subtree..agents/skills/*/SKILL.md— prompts for common agentic workflows.
- Avoid rot. Rot confuses agents and wastes context. When a doc is out of
date with the code: update it (if recent and the change is small) or archive
it to
.agents/projects/<YYYYMMDD>_<filename>.md(if historical-only; date from the first commit viagit). The code is the source of truth. - Context quality and quantity are paramount. Model performance degrades on
a full context window. Agent docs should focus on:
- "Negative guidance": assume agents are smart; document sharp edges based on observed suboptimal agent behavior.
- Using markdown as indexes/ToC for context efficiency ("for X, read file Y").
Common issues
- Stale design docs that guided initial system design — move to
.agents/projects/<YYYYMMDD>_<filename>.md, dated from the first commit (git).
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.
- 4d ago First seen · 43 lines · 27 tokens per session scan A 5018111e5c43
fix-docs is a skill published in the GitHub repository marin-community/marin (3,354 stars, last pushed today), licensed Apache-2.0. It adds 27 tokens to every session and 499 once invoked, about $0.0001 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…