Borrowing it
Nothing to install: this file belongs to stark-ai-de/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/stark-ai-de/agent-skills/main/AGENTS.mdgit clone --depth 1 https://github.com/stark-ai-de/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/stark-ai-de/agent-skills/agents-md)<a href="https://agentmods.dev/instructions/stark-ai-de/agent-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/stark-ai-de/agent-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 5.1 | $0.01275 | $0.01275 |
| Opus 5 | $0.00638 | $0.00638 |
| Sonnet 5 | $0.00255 | $0.00255 |
| Haiku 4.5 | $0.00128 | $0.00128 |
Grade A, and why
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 8d 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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
This repository contains public Agent Skills.
Rules
- Follow the Agent Skills specification: https://agentskills.io/specification.
- Follow the Agent Plugins specification for repository-managed portable plugins: https://agent-plugins.org/specification.
- Keep client-native plugin packages that cannot share the portable root contract in separate generated adapter projections, as required by ADR-0043 (Long, canonical · Guide).
- Do not commit
adapters/. Generate OpenAI-native packages into disposable staging and archive them underdist/openai/withnpm run package:openai-plugin;npm run sync:openai-pluginis a refuse-redirect. - Follow
docs/listing/openai/stark-ai-developer-first-publication.mdfor OpenAI portal upload and first-publication observations. - Bundled
agents/openai.yamlis canonical skill-local metadata. Copy it unchanged into projections; do not adapter-overlay, rewrite, or generate it. - Edit bundled skills only under
skills/<category>/<skill>/. Do not editplugins/stark-ai-developer/by hand, including copies underplugins/stark-ai-developer/skills/. After changing a bundled skill orplugins/stark-ai-developer.source.json, runnpm run sync:agent-plugin. Confirm withnpm run validate:projectionswhen the portable contract changed. - Every skill must have
SKILL.mdwith validnameanddescription. - Skill folder names must match frontmatter names.
- Do not include secrets, tokens, customer data, private repo paths, or internal hostnames.
- Keep
SKILL.mdfiles concise and operational. - Move long examples, rubrics, and templates into
references/orassets/. - Prefer read-only scripts. Any script that modifies files must be clearly documented.
- Document repo-level decisions in
docs/adrs/. - Store every repository ADR as linked
.short.md,.long.md, and.guide.mdfiles. Long is canonical; Short is a faithful abstraction; Guide is non-normative. - Keep one decision per ADR and do not impose numeric word, paragraph, or section limits.
- Keep accepted ADR IDs, filename stems, and decision text stable; change architecture through a reciprocal successor ADR, not an in-place decision rewrite.
- Treat Accepted repository ADRs as binding. If a user requests a conflicting change, name the conflict, warn visibly, and stop the affected implementation until an adaptation or successor decision is accepted.
- Stable public skills with multiple material workflows must expose their complete finite options. Select, explain, and proceed when task intent and existing authority are clear; ask on bare or materially ambiguous invocation, and never infer mutation beyond the user's requested outcome and scope, as required by ADR-0038.
- The 2026-07-31 Architecture Compass setup receipt is preserved as historical, non-normative evidence. It is stale for current proof; ADR-0041 (Long, canonical · Guide) records the current AC-ADR-049 adaptation, and accepted local ADRs remain authoritative.
- Follow
docs/specs.mdfor spec persistence, ADR linkage, filename examples, and repo-facing documentation update rules. - Do not copy copyrighted skill text from other repositories. Use them only as inspiration.
- Do not vendor already-published third-party skills into
skills/; install them project-locally withnpx skills. - Do not stage files with
git addunless the user explicitly asks. - Do not unstage files or otherwise change Git index state unless the user explicitly asks.
- Follow ADR-0029 (Long, canonical · Guide) for agent worktrees: any agent writing repository state uses one assigned worktree under
<root>/.worktrees/<repo>-worktrees/as its working directory and write scope; the canonical checkout and sibling worktrees are read-only to that writer by default. - Worktree enforcement state: repository instructions define the invariant; no shared writable root is configured because granting
<root>/.worktrees/<repo>-worktrees/to every worker would permit cross-worktree writes. Launch each writing agent in its assigned worktree and enforce that workspace as the only repository write scope where the host supports it. Re-check this state only when host capabilities or repository policy change. - Select checks from changed contracts, owning boundaries, and explicit requirements. Reuse only exact, current evidence. Run the local
npm run validateaggregate for release intent or when a mandatory repository, ADR, user, or approved risk-plan gate requires it; do not run it merely because work is being finalized. Honor an explicit user exclusion while reporting any resulting evidence gap, as required by ADR-0041 (Long, canonical · Guide).
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.
- 8d ago First seen · 35 lines · 1,275 tokens per session scan A 61f50ad82720
agent-skills AGENTS.md is an instructions file published in the GitHub repository stark-ai-de/agent-skills (5 stars, last pushed today), licensed Apache-2.0. It adds 1,275 tokens to every session, about $0.0064 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
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.