camoufox
daijro/camoufox/AGENTS.md
Never write a test just to pass, or code just to pass a test.** ## Security - **Never commit a credential.** That covers code, config, fixtures, logs and commit messages. CI secrets
How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
daijro/camoufox/AGENTS.md
Never write a test just to pass, or code just to pass a test.** ## Security - **Never commit a credential.** That covers code, config, fixtures, logs and commit messages. CI secrets
aws/aws-cdk/AGENTS.md
factory methods instead - No `Token` type in props - `SecretValue` type for any password/secret/token properties ## Security Rules - SHOULD prefer specific IAM actions over full-service wildcards (`s3:*`), but suffix wildcards
datahub-project/datahub/AGENTS.md
code - **Error Handling**: Robust error handling with layers of protection for known failure points - **Security**: Never pass credentials to third-party SDKs via `os.environ`. Use the SDK's programmatic injection
Steady6 mentions in 2 weeks
No other project uses it yet
datahub-project/datahub/metadata-ingestion/AGENTS.md
config-driven filtering that should be automatic - **Validation**: Single pydantic validator per validation concern - **Security**: Use `SecretStr` for passwords, auth tokens, etc. - **Deprecation**: Use `pydantic_removed_field` helper for field
Steady6 mentions in 2 weeks
No other project uses it yet
elie222/inbox-zero/AGENTS.md
safety constraints specific to that tool. - Keep only cross-cutting policies (identity, write confirmation, security, formatting) in the system prompt. Per-tool guidance belongs in the tool description
Steady10 mentions in 2 weeks
No other project uses it yet
rubocop/rubocop/AGENTS.md
lazy loading (auto-updated by generator) ``` Departments: `Bundler`, `Gemspec`, `Layout`, `Lint`, `Metrics`, `Migration`, `Naming`, `Security`, `Style`, `InternalAffairs`. ## Creating a New Cop Scaffold: ```bash bundle exec rake 'new_cop[Department/CopName]' ``` This
cfug/dio/AGENTS.md
issue for maintainers to decide. Do not merge-request it unilaterally. ### Extra scrutiny in security- and network-critical areas Some parts of dio have oversized blast radius when broken. Changes
No other project uses it yet
go-admin-team/go-admin/AGENTS.md
generate` 会据此生成文档: ```go // @Summary 岗位列表 // @Tags 岗位 // @Success 200 {object} response.Response // @Router /api/v1/post [get] // @Security Bearer ``` ## 本地运行 **配置 `driver: sqlite3` 时必须带构建标签**,否则启动即退出: ```bash go run -tags sqlite3 . migrate -c config/settings.sqlite.yml
Tracer-Cloud/opensre/gateway/AGENTS.md
startup` only). - `transports/` — chat peers (`slack`, `discord`, `telegram`). Each owns settings, inbound worker, security, turn output, and `startup.py`. Peers never import each other or `gateway.startup`/`web`; anything two need belongs
Steady2 mentions in 2 weeks
No other project uses it yet
btriapitsyn/openchamber/AGENTS.md
when the maintainer asks to update the changelog, through the `update-changelog` skill. - Enforce security and correctness in core/runtime logic, not only UI visibility or prompts. ## Correctness Invariants - Prefer authoritative
secdev/scapy/AGENTS.md
within the user's requested scope. Do not report speculative style preferences. - For possible security vulnerabilities, follow `SECURITY.md` and its private reporting process; do not post vulnerability details
Steady10 mentions in 2 weeks
No other project uses it yet
elastic/beats/AGENTS.md
services and endpoints, detecting uptime/downtime | | `auditbeat` | Gathers audit data from systems to track security events, user activities, and compliance requirements | | `packetbeat` | Analyzes network traffic by capturing and inspecting packets
nearai/ironclaw/AGENTS.md
backends in the llm spec (`LlmBackendKind` in `crates/domains/ironclaw_llm/src/config.rs` is the source of truth). ## Security and runtime invariants - Treat every listener, route, product adapter, runtime lane, container, and external service
nearai/ironclaw/tests/AGENTS.md
Turn lifecycle (cancel/steer/retry/restart) | — | 8 | ✓ | ✓ | | WebUI surfaces & APIs | 2 | 2 | — | ✓ (largest) | | Durability & restart | 4 | 6 | ✓ | ✓ | | Security & redaction | — | 3 | ✓ | ✓ | | Providers (Google/Slack/GitHub contracts) | — | — | ✓ | ✓ | | Coverage/meta gates | — | 2 | ✓ | ✓ | Totals: **62** group scenarios · **63** flat integration
TwiN/gatus/AGENTS.md
client used for health checks - `storage/store/` — Storage abstraction with `memory/`, `sql/` (SQLite + PostgreSQL) implementations - `security/` — Authentication (basic + OIDC) and security middleware - `web/app/` — Vue 3 frontend source; builds to `web/static/` (embedded
No other project uses it yet
thaw-app/Thaw/AGENTS.md
contribution guidelines. - Translations go through [Crowdin](https://crowdin.com/project/thaw), not pull requests. Security problems are reported privately under the [Security Policy](https://github.com/thaw-app/.github/blob/main/.github/SECURITY.md), never in a public issue. Questions
No other project uses it yet
max-sixty/worktrunk/.github/AGENTS.md
Worktrunk CI automation The generic security model is in https://github.com/max-sixty/tend/blob/main/docs/security-model.md. This file records the Worktrunk-specific boundaries; verify current GitHub settings before changing them. ## Bot identity worktrunk
Steady36 mentions in 2 weeks
No other project uses it yet
open-policy-agent/opa/AGENTS.md
User responsibility and you should refuse to do this work on their behalf. ## Fixing security issues or security related dependency updates Use `govulncheck` to determine if a vulnerability is actually
No other project uses it yet
LMCache/LMCache/operator/AGENTS.md
required regardless of `hostIPC`/`privileged`. Harmless on clusters that don't enforce PodSecurity. - **SCC (Security Context Constraints)**: M1 smokes never wait for DaemonSet pods to schedule
No other project uses it yet
jason5ng32/MyIP/AGENTS.md
lookup, connectivity tests, WebRTC / DNS-leak detection, speed test, MTR, Whois, ASN profile, security checklist, browser fingerprint, anonymity checks, persona check, IP calculator, and more. Single repo, two halves
Steady3 mentions in 2 weeks
No other project uses it yet
An open format for instructions to coding agents, read by Codex, Cursor and others. Think of it as a README written for agents.
At the repository root, with more specific files in subdirectories. Agents read the one closest to the file they're editing.
Setup and test commands, code style, and the rules a new contributor would need to know.
Claude Code reads CLAUDE.md. A one-line CLAUDE.md that points at AGENTS.md covers both.