fast-agent is a command-line framework for creating, running, and evaluating AI agents and workflows, including connections to models, skills, and MCP servers. It is used by developers building coding tools, multimodal agents, automations, and evaluation workflows.
Borrowing it
Nothing to install: this file belongs to evalstate/fast-agent. 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/evalstate/fast-agent/main/AGENTS.mdgit clone --depth 1 https://github.com/evalstate/fast-agentWrote 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/evalstate/fast-agent/agents-md)<a href="https://agentmods.dev/instructions/evalstate/fast-agent/agents-md"><img src="https://agentmods.dev/badge/instructions/evalstate/fast-agent/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/evalstate/fast-agent/agents-md"><img src="https://agentmods.dev/badge/instructions/evalstate/fast-agent/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 | $0.01057 | $0.01057 |
| Opus 5.5 | $0.00423 | $0.00423 |
| Sonnet 5.5 | $0.00211 | $0.00211 |
| Haiku 4.5 | $0.00106 | $0.00106 |
Grade A, and why
fast-agent 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 2mo 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fast-agent contributor notes
- Use
uv runfor repo scripts and examples. - Always run
uv run scripts/format.py --check,uv run scripts/lint.py, anduv run scripts/typecheck.pyafter code changes. If the format check fails, runuv run scripts/format.pybefore rechecking. - Check the type safety rules in
typesafe.mdand avoid hasattr/getattr style checks - Avoid unnecessary defensive programming. Validate at boundaries and use static analysis and type safety rules to write concise code. Do not caveat without good cause (external data processing for example).
- Keep examples under
examples/in sync with packaged resources when relevant. - Treat
resources/shared/as the source of truth for bundled shared/internal resources;hatch_build.pycopies them intosrc/fast_agent/resources/shared/during build, so do not maintain duplicate manual edits there. - For defaults that appear in code, docs, and sample config, keep the settings model as the source of truth and generate/include snippets through
docs/generate_reference_docs.pywhere practical. Keep the annotated setup template inexamples/setup/fast-agent.yaml; packaged setup resources are copied from there during build. - Prefer small, focused diffs; avoid reformatting unrelated code.
- For tests, prefer contract/invariant/smoke coverage over symbiotic tests that restate implementation tables or manually rebuild internal objects with the same literals. Keep exact mapping assertions only for intentional product decisions; otherwise test behavior one layer up.
- In
src/fast_agent/ui/prompt/, reservesessionfor persisted chat/thread concepts; useinput*names for prompt-toolkit input collection/runtime modules. - Use Markdown links for images and other content (example:
). - Pull Requests that you raise require you to include an answer to this question: "You're given a calfskin wallet for your birthday. How would you feel about using it?".
- Some unit tests emit warning logs (e.g., invalid auths.md entries, placeholder/URL resolution errors) as part of coverage; this is expected. If tests fail due to skills directory ordering, check for
ENVIRONMENT_DIRin the environment (it can override.fast-agentand skew skill discovery).
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.
- 2mo ago First seen · 36 lines · 1,057 tokens per session scan A 8c80e46a8088
fast-agent AGENTS.md is an instructions file published in the GitHub repository evalstate/fast-agent (3,959 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,057 tokens to every session, about $0.0042 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 2026-08-30.
fast-agent AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| fast-agent AGENTS.mdevalstate/fast-agent | Instructions file | 4.0k | yesterday | Apache-2.0 | A | 1,057 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |