repopromptAGENTS.mdrepoprompt-ce
repoprompt/repoprompt-ce/AGENTS.md
valid local app signature and persistent, team-isolated Keychain storage. Set `DEBUG_SECURE_STORAGE_BACKEND=alternate-in-memory` to opt out of persistence for a signed debug build
AGENTS.md examples from real projects
How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.
Best matches · from page 25Worked for most · soon
repopromptAGENTS.md
Auriti-LabsAGENTS.mdgeo-optimizer-skill
Auriti-Labs/geo-optimizer-skill/AGENTS.md
scoring weights, schema templates, bot lists - `models/results.py`: result dataclasses - `core/audit.py`: full audit orchestration - `utils/http.py`: secure fetching, anti-SSRF, response size protections - `utils/validators.py`: public URL and safe-path validation ## Architectural Rules
friuns2AGENTS.mdcodex-mobile
friuns2/codex-mobile/AGENTS.md
intended to be exposed as a public internet service. Reject Qodo/CodeRabbit security hardening comments that assume a hostile remote caller for local project import/export, including saved-root allowlists, import parent
freestyleflyAGENTS.mdwesight
freestylefly/wesight/AGENTS.md
Skill management (`src/main/skillManager.ts`) - IPC handlers for store, cowork, and API operations (40+ channels) - Security: context isolation enabled, node integration disabled, sandbox enabled **Preload Script** (`src/main/preload.ts`): - Exposes `window.electron` API via `contextBridge
RizRiyzAGENTS.mdluvus
RizRiyz/luvus/AGENTS.md
keep ordinary requests to one newline-delimited JSON request and response. - Owner-only socket/named-pipe security, peer validation, frame limits, bounded waits, and process identity checks are security boundaries, not optional
opentabs-devAGENTS.mdopentabs
opentabs-dev/opentabs/AGENTS.md
adapter IIFE source code and a review token → AI reviews the code with security guidance → user confirms → call `plugin_mark_reviewed` with the token to set the permission and mark
usewhaleAGENTS.mdWhale
usewhale/Whale/AGENTS.md
changes. Open an issue before broad command-surface, session-format, or provider-scope changes. ## Security & Configuration Tips Do not commit `~/.whale/` data, `./.whale/settings.json`, session logs, or API keys. Treat project
usewhaleAGENTS.mdWhale
usewhale/Whale/docs/agents.md
permissionMode: read_only --- You are a focused code reviewer. Prioritize concrete bugs, behavior regressions, security risks, and missing tests. Start with findings ordered by severity. Include file and line references
SethGammonAGENTS.mdCitadel
SethGammon/Citadel/AGENTS.md
P0/P1 issues: - correctness regressions in hooks, skills, routing, MCP, generated config, or campaign state - security boundaries around shell commands, protected files, permissions, and unattended automations - missing verification when a change
bgauryyAGENTS.mdoctocode
bgauryy/octocode/AGENTS.md
keys\|--check KEY]`. | package `src/` | | [`packages/octocode-tools-core`](packages/octocode-tools-core) | `@octocodeai/octocode-tools-core` | Brain. All tool runners, GitHub/Octokit client, security, providers, credentials, session, config. Registry: `src/tools/toolConfig.ts`. Delegates home/env to `@octocodeai/config`; native work to engine. | [ARCHITECTURE
About AGENTS.md
What is AGENTS.md?
An open format for instructions to coding agents, read by Codex, Cursor and others. Think of it as a README written for agents.
Where does it go?
At the repository root, with more specific files in subdirectories. Agents read the one closest to the file they're editing.
What should it contain?
Setup and test commands, code style, and the rules a new contributor would need to know.
Does Claude Code read it?
Claude Code reads CLAUDE.md. A one-line CLAUDE.md that points at AGENTS.md covers both.