AGENTS.md examples from real projects

caddyserverAGENTS.md

caddy

caddyserver/caddy/AGENTS.md

security-first, modular, extensible server platform. ## Code Style ### Go Idioms Follow [Go Code Review Comments](https://go.dev/wiki/CodeReviewComments): - **Error flow**: Early return, indent error handling—not else blocks

No other project uses it yet

ElasticAGENTS.md

elasticsearch

elastic/elasticsearch/AGENTS.md

breaker reservations, pooled memory allocations, etc) must be released eventually. - When writing or reviewing asynchronous code, consult `docs/internal/Liveness.md` for guidance. ## Logging & Error Handling - Elasticsearch should prefer its own logger `org.elasticsearch.logging.LogManager

No other project uses it yet

storytoldAGENTS.md

photocraft

storytold/photocraft/AGENTS.md

agent answers for what it opens and for its review comments. 2. **Check, then claim.** Before writing code, read the issue comments, search pull requests for `#N` and the keywords

No other project uses it yet

grafanaAGENTS.md

grafana

grafana/grafana/AGENTS.md

security issue reporting page](https://grafana.com/legal/report-a-security-issue/) and not directly in this repository. ## Code Review Rules ### Metrics - Review metric changes against `contribute/backend/instrumentation.md`, especially registration, duplicate registration, label cardinality

No other project uses it yet

rohitg00Deletes or force-pushesAGENTS.md

ai-engineering-from-scratch

rohitg00/ai-engineering-from-scratch/AGENTS.md

interview loop for a role, or a review of interview gaps, read and follow `skills/interview-prep/SKILL.md` before asking anything. Claude Code also discovers the copy under `.claude/skills/`. The skill asks

No other project uses it yet

colbymchenryDeletes or force-pushesAGENTS.md

codegraph

colbymchenry/codegraph/AGENTS.md

summing per-turn assistant usage**, not `result.usage` (last-turn only in current Claude Code). See `docs/benchmarks/call-sequence-analysis.md`.) The mechanism that drives everything here: **an agent falls back to Read/Grep the instant

No other project uses it yet

OpenAIReads credentialsAGENTS.md

openai-cookbook

openai/openai-cookbook/AGENTS.md

article, Markdown or MDX file, and notebook Markdown cell. For editorial notebook changes, preserve code cells, outputs, execution counts, attachments, cell order, and metadata. Fix safe issues, rerun the relevant

No other project uses it yet

hugohe3AGENTS.md

ppt-master

hugohe3/ppt-master/AGENTS.md

slides untouched also use [`edit-native-pptx`](skills/ppt-master/workflows/edit-native-pptx.md); export must report `rebuilt=0`. - [`visual-review`](skills/ppt-master/workflows/stages/visual-review.md), [`customize-animations`](skills/ppt-master/workflows/stages/customize-animations.md), and [`generate-audio`](skills/ppt-master/workflows/stages/generate-audio.md) are supporting stages; their trigger rules remain

No other project uses it yet

usestrixPipes a download into a shellAGENTS.md

strix

usestrix/strix/AGENTS.md

files, 25 MiB/file, 250 MiB expanded, 50 MiB compressed. Source-only infers `code_review`; source plus a domain infers `live_test`. - The temporary local archive is always removed. A staged

No other project uses it yet

tw93Deletes or force-pushesAGENTS.md

Mole

tw93/Mole/AGENTS.md

eval; risk follows paths** (2026-10-26, from the Claude Code team's code review write-up). A fix for anything a user or a published release met adds

No other project uses it yet

strapiAGENTS.md

strapi

strapi/strapi/AGENTS.md

watch-admin # terminal 2 ``` --- ## Build ```bash yarn build # all packages (code + types) yarn build:code # faster — skips .d.ts generation yarn nx build @strapi/admin # single package ``` --- ## Testing ### Unit tests (fastest

No other project uses it yet

strapiAGENTS.md

strapi

strapi/strapi/docs/AGENTS.md

Verify every claim against the code before you remove a `status`. If you cannot verify a claim, keep the status and add a `review_notes` item

No other project uses it yet

mobyAGENTS.md

moby

moby/moby/AGENTS.md

pull requests. It is the source of truth for contribution scope, coding style, testing, commits, DCO sign-off, review, AI usage, and release notes. # Pull requests When opening a pull

No other project uses it yet

remotion-devAGENTS.md

remotion

remotion-dev/remotion/AGENTS.md

found in `packages/core/src/version.ts`. The next version should increment the patch version by 1. ## Coding style - Keep things in one function unless they are composable or reusable. - Do not extract single

No other project uses it yet

ansibleAGENTS.md

ansible

ansible/ansible/AGENTS.md

negotiable -- licensing violations can create serious legal issues for the project. ## General Principles When reviewing code, don't flag issues that `ansible-test sanity` already catches. Focus review effort

No other project uses it yet

code-yeongyuAGENTS.md

oh-my-opencode

code-yeongyu/oh-my-opencode/.agents/AGENTS.md

only issue/PR triage with evidence reports | | `hyperplan/` | yes | Adversarial multi-agent planning | | `pre-publish-review/` | yes | 12-agent pre-publish release gate | | `get-unpublished-changes/` | NEW | Skill form

code-yeongyuReads credentialsAGENTS.md

oh-my-opencode

code-yeongyu/oh-my-opencode/AGENTS.md

REAL `senpi` binary through the drivers in `packages/omo-senpi/scripts/qa/`, which build their own isolated `SENPI_CODING_AGENT_DIR` and IGNORE a caller-provided one, so the real `~/.senpi/agent` is NEVER written

code-yeongyuAGENTS.md

oh-my-opencode

code-yeongyu/oh-my-opencode/.opencode/AGENTS.md

Adversarial multi-agent planning. 5 hostile category members cross-critique, lead synthesizes. | | `pre-publish-review/` | Nuclear-grade 12-agent pre-publish release gate. Runs `/get-unpublished-changes`, spawns ultrabrain agents per change

docling-projectAGENTS.md

docling

docling-project/docling/AGENTS.md

communicate with the user. Use short sentences, active voice, and consistent terms. Keep code identifiers, API names, and quoted source text exact. State the result and any limits clearly. ## Project

No other project uses it yet

openinterpreterAGENTS.md

open-interpreter

openinterpreter/open-interpreter/AGENTS.md

your new functionality. Refactor existing code as necessary to make this happen. Likewise, when reviewing code, do not hesitate to push back on PRs that would unnecessarily add code