Borrowing it
Nothing to install: this file belongs to dboeckli/ai-agent-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/dboeckli/ai-agent-skills/master/AGENTS.mdgit clone --depth 1 https://github.com/dboeckli/ai-agent-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/dboeckli/ai-agent-skills/agents-md)<a href="https://agentmods.dev/instructions/dboeckli/ai-agent-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/dboeckli/ai-agent-skills/agents-md/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/instructions/dboeckli/ai-agent-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/dboeckli/ai-agent-skills/agents-md.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 | $0.01263 | $0.01263 |
| Opus 5.5 | $0.00505 | $0.00505 |
| Sonnet 5.5 | $0.00253 | $0.00253 |
| Haiku 4.5 | $0.00126 | $0.00126 |
Grade A, and why
ai-agent-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 1mo 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — AI Agent Skills Repository
This is a SKILL.md package — a collection of reusable AI-agent skills, not an application. No application build exists, but skills and docs are validated and formatted — see below.
Build & verify commands
- Validate SKILL.md frontmatter:
bash .claude/skills/skill-best-practices/scripts/validate-skills.sh - Validate CLAUDE.md (required sections + skill table sync):
bash .claude/skills/cc-best-practices/scripts/validate-claude-md.sh - Format (Prettier + shfmt, Stop hook):
bash .claude/hooks/format.sh - CI:
.github/workflows/validate-skills.ymlruns the validators on push/PR and publishes the npm package to GitHub Packages.
After changing a skill or doc, always verify: run the relevant command above and report its output (evidence, not just "done").
Sandbox (opencode-sandbox-kit)
Run this repo inside an opencode-sandbox-kit sandbox — canonical, multiline, no --name,
workspace mount ., --skills=off, --static-mcp idea, pinned template:
sbx run opencode `
--kit "git+https://codeberg.org/dboeckli/opencode-sandbox-kit.git#dir=opencode-agent" `
--template docker.cloudsmith.io/dboeckli/sbx/sbx-opencode-tooling:latest `
--skills=off `
--static-mcp idea `
.
Claude Code / Mammouth Code variants and the sbx kit add command are documented in README.md.
Sandbox quirk (background)
The sandbox mounts the repo via filesystem passthrough, which blocks symlinks — npm installs would fail with EPERM unless bin links are skipped. The sandbox kit sets npm_config_bin_links=false globally, so no manual export is needed here.
Repository Structure
.claude/skills/<skill-name>/
SKILL.md # required: YAML frontmatter + Markdown instructions
references/ # optional: supporting docs loaded on demand
scripts/ # optional: executable Bash/Python helpers
assets/ # optional: templates, fonts, icons
Skills
| Skill | Trigger |
|---|---|
camel-matrix |
"generate camel matrix", "update camel compatibility" — runs .claude/skills/camel-matrix/scripts/camel-springboot-matrix.sh, outputs target/camel-springboot-matrix.md |
cc-best-practices |
Questions about effective Claude Code usage, context management, prompting |
cron-schedule-planner |
"when do my cron actions run", "do my scheduled builds collide" — runs .claude/skills/cron-schedule-planner/scripts/cron-schedule-planner.sh, outputs target/cron-schedule-overview.md |
project-references |
Look up conventions from sibling repos under ~/projects/referenzen/ |
skill-best-practices |
Creating, reviewing, or troubleshooting SKILL.md files |
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.
- 1mo ago Changed · +5 tokens per session e86d6cfcc738
- 1mo ago Changed · -3 tokens per session 0bac92df17fa
- 1mo ago Changed · +17 lines · +203 tokens per session 00300b969a7c
- 2mo ago First seen · 83 lines · 1,058 tokens per session scan A ecd595b51c37
ai-agent-skills AGENTS.md is an instructions file published in the GitHub repository dboeckli/ai-agent-skills (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,263 tokens to every session, about $0.0051 per session on Opus 5.5. 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.