awesome-ai-agents is a curated directory of open-source projects and other resources for building AI agents, software that can carry out tasks through repeated model-driven actions. It is for people exploring agentic AI tools and projects that maintain a public code repository.
Borrowing it
Nothing to install: this file belongs to slavakurilyak/awesome-ai-agents. 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/slavakurilyak/awesome-ai-agents/main/AGENTS.mdgit clone --depth 1 https://github.com/slavakurilyak/awesome-ai-agentsWrote 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/slavakurilyak/awesome-ai-agents/agents-md)<a href="https://agentmods.dev/instructions/slavakurilyak/awesome-ai-agents/agents-md"><img src="https://agentmods.dev/badge/instructions/slavakurilyak/awesome-ai-agents/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/slavakurilyak/awesome-ai-agents/agents-md"><img src="https://agentmods.dev/badge/instructions/slavakurilyak/awesome-ai-agents/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 | $0.00403 | $0.00403 |
| Opus 5.5 | $0.00161 | $0.00161 |
| Sonnet 5.5 | $0.00081 | $0.00081 |
| Haiku 4.5 | $0.00040 | $0.00040 |
Grade A, and why
awesome-ai-agents 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 12d 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
Agent guidance
Third-party project eligibility
Every project added to the list must have its own public repository on GitHub, GitLab.com, or Codeberg. No specific license is required. A hosted product, website, forge organization profile, client, or integration without the project's own public repository does not qualify. Never treat a contributor-supplied boolean or license claim as verification; for an individual submission, run go run ./cmd/verify-forge-repositories --project "Project name" and go run ./cmd/validate-data --project "Project name". Require successful public repository metadata. Failed, private, or inaccessible checks mean unverified and ineligible. Do not scan the full catalog for a single-project change. Full-catalog audits require the explicit --all flag.
The repository must also show recent project maintenance: at least one substantive, non-automated commit to its default branch within the six months before review. Check the default branch's commit history; do not use repository updated_at, stars, or bot-only dependency/metadata changes as evidence of project maintenance. If the activity window is exceeded, the contribution is ineligible and may be closed.
Crediting every addition
Every project added to the catalog needs a submitted_by record in contributions.json before merge. Credit the author of the issue or pull request it came from. For a direct-addition PR with no earlier submission, the PR author is the submitter; the maintainer should record that automatically from GitHub with go run ./cmd/contributions record-direct-pr --project "Project name" --pr <pull-request-number>. When a maintainer asks for an addition directly, credit that maintainer and use the addition pull request as the evidence. A new entry must never show "not yet recovered" as its submitter. Run go run ./cmd/contributions validate --project "Project name" for each added project; it fails when the record is missing.
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.
- 12d ago Changed · -10 lines · -308 tokens per session d4089d646fa1
- 15d ago Changed · +2 lines · +148 tokens per session 582f1bade413
- 16d ago Changed · +4 lines · +109 tokens per session 0062869d9bee
- 21d ago First seen · 16 lines · 454 tokens per session scan A e012efc83ba6
awesome-ai-agents AGENTS.md is an instructions file published in the GitHub repository slavakurilyak/awesome-ai-agents (2,446 stars, last pushed 12d ago), licensed MIT. It adds 403 tokens to every session, about $0.0016 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 2026-09-25.
Other instructions, from other repositories
kodama conventions.md
Instructions for amergrgic/kodama, a project described as: Multi-agent pack for the Kiro CLI — one orchestrator, eight specialists, zero lock-in.
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.