AGENTS.mdA

AGENTS.md from benchflow-ai/benchflow is an AGENTS.md file: the standing instructions coding agents read in that repo.

Install it, pinned
mdr add benchflow-ai/benchflow/AGENTS.md@git:20260816.6398f31

Pins git:20260816.6398f31 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 14 of 14 checks passed
Kind
AGENTS.md file
Repository
benchflow-ai/benchflow
Path
AGENTS.md
Versions recorded
5
Latest version
git:20260816.6398f31, committed Aug 16, 2026
First version recorded
Jun 4, 2026
Size
6,509 bytes
Repository stars
359
License
Apache-2.0

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# benchflow

Multi-turn agent benchmarking with ACP. Docs live in [`docs/`](./docs/).

## Setup + test

```bash
uv sync --extra dev --locked
uv run python -m pytest tests/
uv run ty check src/
uv run ruff check .
```

## Conventions

- **Don't rewrite passing tests** to match new behavior. Update for shape changes, not for semantic changes you don't understand. No tautological tests.
- **Regression tests must name the PR/commit they guard** in the docstring (e.g. `Guards the fix from PR #198 against the regression introduced by PR #193`).
- **Human review before `main`.** PRs only. No force-pushes to `main`. Self-approval doesn't count.
- **Trunk-based:** branch off `main`, PR back to `main`. No long-lived release branches.
- **Releases:** current mechanics live in [`docs/release.md`](./docs/release.md). Merges to `main` publish internal preview `.devN` builds after CI passes; public releases require a reviewed stable-version PR, a matching `v<version>` tag on `main`, then a bump back to the next `.dev0`.

## Experiment guidance (when using benchflow to run batch tasks experiments)
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add benchflow-ai/benchflow/AGENTS.md@sha256:7621eedb77a17ed5

The line at the top of this page pins the label git:20260816.6398f31, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_dmttc46vk65xujca.svg)](https://markdownregistry.com/a/art_dmttc46vk65xujca)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between Jun 4, 2026 and Aug 16, 2026, about one every 18 days.

versioncommittedcommitsizeaudit
git:20260816.6398f31 latest2026-08-16 6398f31 6,509 BA view · diff
git:20260815.898de302026-08-15 898de30 6,101 BA view · diff
git:20260804.fa016e62026-08-04 fa016e6 4,783 BA view · diff
git:20260615.17f2a622026-06-15 17f2a62 4,972 BA view · diff
git:20260604.159edd22026-06-04 159edd2 4,892 BA view

Audit of the latest version

A  14 of 14 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Size between 200 bytes and 200 KB (6509 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

benchflow-ai/benchflow · 359 stars · license Apache-2.0 · pushed 2026-10-30 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_dmttc46vk65xujca
GET https://markdownregistry.com/api/v1/resolve?ref=benchflow-ai/benchflow/AGENTS.md
GET https://markdownregistry.com/api/v1/blob/7621eedb77a17ed59a4f530c1219ff26a695a7dc28d251d09797a193ae968fae

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: how to write a good AGENTS.md · AGENTS.md vs CLAUDE.md · which agent file does what.

More from benchflow-ai/benchflow

benchflow-experiment-review SKILL.md skill
benchflow-ai/benchflow · .agents/skills/benchflow-experiment-review/SKILL.md · Review Benchflow or SkillsBench task-run trajectories and integration-test Benchflow code changes. Use this skill…
git:20260822.656ec91 · audit A · 359 stars
benchflow-traj-upload-ops SKILL.md skill
benchflow-ai/benchflow · .agents/skills/benchflow-traj-upload-ops/SKILL.md · Operate, test, troubleshoot, and explain `bench traj upload` for public or trusted-direct trajectory contributions…
git:20260816.b67af9e · audit A · 359 stars
benchflow-traj-upload SKILL.md skill
benchflow-ai/benchflow · .agents/skills/benchflow-traj-upload/SKILL.md · Find a local Claude Code or Codex session, open the BenchFlow trajectory viewer, and submit it after the user reviews…
git:20260816.96b1e65 · audit A · 359 stars
benchflow SKILL.md skill
benchflow-ai/benchflow · .agents/skills/benchflow/SKILL.md · Run agent benchmarks, create tasks, analyze results, and manage agents using BenchFlow. Use when asked to benchmark an…
git:20260920.6b99a10 · audit A · 359 stars
benchflow SKILL.md skill
benchflow-ai/benchflow · .agents/skills/benchflow/tasks/benchflow-knowledge/environment/benchflow/SKILL.md · Run agent benchmarks, create tasks, analyze results, and manage agents using BenchFlow. Use when asked to benchmark an…
git:20260706.2ea084b · audit A · 359 stars
benchflow SKILL.md skill
benchflow-ai/benchflow · .agents/skills/benchflow/tasks/create-simple-task/environment/benchflow/SKILL.md · Run agent benchmarks, create tasks, analyze results, and manage agents using BenchFlow. Use when asked to benchmark an…
git:20260706.2ea084b · audit A · 359 stars
skill-creator SKILL.md skill
benchflow-ai/benchflow · .agents/skills/skill-creator/SKILL.md · Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a…
git:20260816.6398f31 · audit A · 359 stars
task-creator SKILL.md skill
benchflow-ai/benchflow · .agents/skills/task-creator/SKILL.md · SkillsBench task authoring — walk a contributor from idea to submission-ready task following CONTRIBUTING.md and the…
git:20260815.898de30 · audit A · 359 stars
task-review SKILL.md skill
benchflow-ai/benchflow · .agents/skills/task-review/SKILL.md · SkillsBench task PR review — classifies the task track (standard / research / multimodal), runs static policy checks…
git:20260815.898de30 · audit A · 359 stars
thermo-nuclear-code-quality-review SKILL.md skill
benchflow-ai/benchflow · .agents/skills/thermo-nuclear-code-quality-review/SKILL.md · Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth…
git:20260815.898de30 · audit A · 359 stars
CLAUDE.md CLAUDE.md file
benchflow-ai/benchflow · CLAUDE.md
git:20260515.7f58eb1 · audit B · 359 stars
independent-review SKILL.md skill
benchflow-ai/benchflow · benchmarks/followup-bench/SKILL.md · Incorporate feedback from an independent code reviewer to improve your solution. The reviewer is a different agent that…
git:20260420.eb5b1af · audit A · 359 stars

Every file in benchflow-ai/benchflow

Other files named AGENTS.md

AGENTS.md AGENTS.md file
morluto/rea · AGENTS.md
git:20261101.d684125 · audit A · 417,919 stars
AGENTS.md AGENTS.md file
obra/superpowers · AGENTS.md
git:20261020.b739a8a · audit A · 309,852 stars
AGENTS.md AGENTS.md file
affaan-m/ecc · AGENTS.md
git:20261030.f29e332 · audit A · 293,827 stars
AGENTS.md AGENTS.md file
firecrawl/firecrawl · AGENTS.md
git:20261008.5a75dca · audit A · 198,353 stars
AGENTS.md AGENTS.md file
dietrichgebert/ponytail · AGENTS.md
git:20261008.2a1fe84 · audit A · 182,080 stars
AGENTS.md AGENTS.md file
graphify-labs/graphify · AGENTS.md
git:20260926.98d73fe · audit A · 139,879 stars
AGENTS.md AGENTS.md file
garrytan/gstack · AGENTS.md
git:20261027.a50cf58 · audit A · 138,879 stars
AGENTS.md AGENTS.md file
juliusbrussee/caveman · AGENTS.md
git:20260902.d9faebc · audit A · 116,476 stars

Browse by kind, by grade A, or by owner.