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 instructions/vanducng/skills/agents-mdgit clone --depth 1 https://github.com/vanducng/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/instructions/vanducng/skills/agents-md)<a href="https://agentmods.dev/instructions/vanducng/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/vanducng/skills/agents-md.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 | $0.00971 | $0.00971 |
| Opus 5 | $0.00485 | $0.00485 |
| Sonnet 5 | $0.00194 | $0.00194 |
| Haiku 4.5 | $0.00097 | $0.00097 |
Grade A, and why
skills AGENTS.md 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
This repository is a daily-driver collection of skills for agentic coding, described by skills.toml. Skill packages live under skills/<name>/ and each package must include SKILL.md with valid frontmatter. Skill-specific scripts, references, and assets stay inside that skill directory, for example skills/file-browser/scripts/ and skills/file-browser/assets/. Repository helpers live in scripts/ (install/uninstall/validate/check-*). The vd CLI that installs and manages these skills lives in a separate repo, not here. Agent-generated working artifacts (reports, plans, visuals, journals, state) live under a gitignored .workbench/ umbrella when the project opts in via .vd.json (paths.umbrella); otherwise the legacy plans/ layout applies. With paths.layout: feature-first set, those artifacts nest per-feature under .workbench/features/{ticket}-{slug}/{plans,reports,visuals,journals,state}/ (plus root-level _global/ and _archive/), managed by the workbench skill, instead of flat type-first siblings. Producer skills always write to the hook-injected Reports:/Plans:/Visuals:/Journals: paths - never construct the layout by hand (enforced by scripts/check-skill-paths.sh).
Build, Test, and Development Commands
bash scripts/new-skill.sh my-new-skill: scaffold a new skill directory.bash scripts/validate.sh: validate everyskills/*/SKILL.mdfrontmatter block.bash scripts/install.sh/scripts/uninstall.sh: install/remove the skills locally (Claude Code dev symlinks into~/.claude/skillsonly; usevd install codexfor the Codex~/.agents/skillsnamespace).bash scripts/check-docs-site.sh --check: verifydocs/tracks the catalog.bash scripts/check-install-conflicts.sh: check for skill ID/file conflicts.cd skills/file-browser && npm test: run the file-browser server tests.cd skills/file-browser && npm start: run the local file-browser server.
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 · 42 lines · 971 tokens per session scan A 301664ad1f88
skills AGENTS.md is an instructions file published in the GitHub repository vanducng/skills (7 stars, last pushed yesterday), licensed MIT. It adds 971 tokens to every session, about $0.0049 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 instructions, from other repositories
atelier AGENTS.md
AGENTS.md instructions for martinffx/atelier, covering agents.md, repository overview, skills structure, skill file format and namespace philosophy.
claude-code-codex-bridge AGENTS.md
Instructions for vladolaru/claude-code-codex-bridge, covering agents.md, repository overview, architecture, repository structure and package layout.
agents AGENTS.md
Instructions for denysdovhan/agents, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
the-loop CLAUDE.md
Claude Code instructions for MadaraUchiha-314/the-loop, covering claude.md — working in the-loop's own repository, why this file exists and what to do.
slow-powers AGENTS.md
Instructions for slowdini/slow-powers, covering slow-powers, what lives here, editing the right files, cross-harness compatibility and pull request requirements.
Tracework AGENTS.md
AGENTS.md instructions for KKenny0/Tracework, covering agents.md, what this is, configuration, repository structure and skills overview.