Borrowing it
Nothing to install: this file belongs to Birfy/agentdescent. 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/Birfy/agentdescent/main/AGENTS.mdgit clone --depth 1 https://github.com/Birfy/agentdescentWrote 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/birfy/agentdescent/agents-md)<a href="https://agentmods.dev/instructions/birfy/agentdescent/agents-md"><img src="https://agentmods.dev/badge/instructions/birfy/agentdescent/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/birfy/agentdescent/agents-md"><img src="https://agentmods.dev/badge/instructions/birfy/agentdescent/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 | $0.02582 | $0.02582 |
| Opus 5.5 | $0.01033 | $0.01033 |
| Sonnet 5.5 | $0.00516 | $0.00516 |
| Haiku 4.5 | $0.00258 | $0.00258 |
Grade A, and why
agentdescent 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 9d 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Instructions for AI coding agents working on Birfy/agentdescent. Human
contributors: CONTRIBUTING.md has the same rules with more
background. The owner and only maintainer is Danyang (GitHub Birfy).
Before you code
- Read LESSONS.md. Open lessons are constraints.
- Read CODE_STANDARDS.md: Verifier honesty, tests that
fail on
main, offline tests, generated files, the merge gate. - Keep the Hard rules below.
Pipeline contract
One issue → one fresh clone → one branch → one PR → green CI → review → merge by tier.
- Issue. Work one
agent-readyissue per session, in a fresh clone (git clone https://github.com/Birfy/agentdescent <run-dir>/repo), never in a shared or stale checkout. - Branch from the latest
origin/main. Write a test that fails onmain, then fix the class of bug, not the one sample. - Verify locally at the tip:
pip install -e ".[dev]",pytest -q, andmkdocs build --strictwhendocs/ormkdocs.ymlchanged (see Commands). - PR to
main. Imperative English title (fix(runstore): …,feat(cli): …, as ingit log),Fixes #Nin the body, and the PR template'sTip SHA:/Ran:/Not run:lines. A user-visible change adds one fragmentchangelog.d/<issue>-<slug>.md(changelog.d/README.md); never editCHANGELOG.mdin a PR. Squash is the only merge method and the squash commit is the PR title + body, so keep the body short. - CI. The required checks are
build(docs) andtest (3.9)…test (3.13). Never merge around a red or pending check.risk tierandreviewed tipare report-only and are not required. - Review and merge by tier; see Merge policy.
- Stop and hand over to Danyang on a security-sensitive change, an unresolved design decision, or when you cannot get a green tip.
When a class of mistake repeats, date a lesson in LESSONS.md (Seen N×); after
≥3 days promote the durable rule into CODE_STANDARDS.md / CONTRIBUTING.md.
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.
- 9d ago First seen · 177 lines · 2,582 tokens per session scan A 4622a0b87b70
agentdescent AGENTS.md is an instructions file published in the GitHub repository Birfy/agentdescent (201 stars, last pushed today), licensed MIT. It adds 2,582 tokens to every session, about $0.0103 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 2026-10-20.
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).
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.