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 skills add vosslab/vosslab-skills --skill agents-md-fixergit clone --depth 1 https://github.com/vosslab/vosslab-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/vosslab/vosslab-skills/agents-md-fixer)<a href="https://agentmods.dev/skills/vosslab/vosslab-skills/agents-md-fixer"><img src="https://agentmods.dev/badge/skills/vosslab/vosslab-skills/agents-md-fixer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/vosslab/vosslab-skills/agents-md-fixer"><img src="https://agentmods.dev/badge/skills/vosslab/vosslab-skills/agents-md-fixer.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00055 | $0.01851 |
| Opus 5 | $0.00028 | $0.00925 |
| Sonnet 5 | $0.00011 | $0.00370 |
| Haiku 4.5 | $0.00006 | $0.00185 |
Grade A, and why
agents-md-fixer 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 10d 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md fixer
Goal
Make AGENTS.md a tiny pointer file. It should mostly be bare path pointers
into docs/*.md, not prose. The longer AGENTS.md grows, the worse AI coding
agents perform: they skim, prioritize poorly, and miss the load-bearing
rules. This skill audits AGENTS.md and returns an aggressively tightened
version, with the manager (the invoking agent) exercising judgment about
what is important for this repo versus frivolous.
AGENTS.md is written for AI agents, not humans. Do NOT use Markdown links
([text](path)); reference docs by bare path (docs/PYTHON_STYLE.md) so the
file stays plain for the agents that read it. Clickability on GitHub is a
human concern and is not a goal here.
Size guidance (line count is a rough proxy, not a contract; "line" means a non-blank text line in the rendered Markdown):
- Prefer about 15 lines or fewer.
- Hard cap at about 50 lines. If the file is longer, something belongs in
docs/*.mdinstead. - The shorter the better. A 10-line
AGENTS.mdthat links to the right docs is better than a 40-line one that restates them.
If a rule has a canonical home in docs/*.md, point to it by path, do not
restate. The docs/REPO_STYLE.md "AGENTS.md files" section describes the
philosophy.
Required content (keep)
Keep only items that are repo-specific and load-bearing:
- Bare path pointers to canonical style docs that exist in this repo, for example
docs/REPO_STYLE.md,docs/PYTHON_STYLE.md,docs/MARKDOWN_STYLE.md,docs/PYTEST_STYLE.md, anddocs/CHANGELOG.md. - Repo-specific runtime quirks: interpreter bootstrap, env activation, container entry, non-default install paths.
- Non-obvious workflow constraints actually enforced in this repo (example:
"humans run
git commit", branch policy, hook behavior). - Test invocation cheat-line specific to this repo.
- Any user-injected directive marked as overriding defaults (preserve it verbatim).
Frivolous content (cut or move)
Flag and remove these patterns:
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.
- 10d ago First seen · 166 lines · 55 tokens per session scan A df7bb9af735b
agents-md-fixer is a skill published in the GitHub repository vosslab/vosslab-skills (2 stars, last pushed 14d ago), licensed MIT. It adds 55 tokens to every session and 1,851 once invoked, about $0.0003 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.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…