AGENTS.md examples from real projects

Yakoub-aiAGENTS.md

Tech-Skills / security

Yakoub-ai/Tech-Skills/skills/security/AGENTS.md

Coordinates security and compliance - manages Security Architects, Compliance Officers, and Security Hardeners

Agent-Rules-EcosystemAGENTS.md

security-agent-skill

Agent-Rules-Ecosystem/security-agent-skill/AGENTS.md

Transversal Cybersecurity, SecOps, OWASP Audit, Secret Scanning, and Encryption Skill for AI Agents.

aspose-wordsAGENTS.md

agentic-net-examples / security-and-protection

aspose-words/agentic-net-examples/security-and-protection/AGENTS.md

Verified C# examples for security-and-protection scenarios in Aspose.Words for .NET

aspose-pdfAGENTS.md

agentic-net-examples / facades-secure-documents

aspose-pdf/agentic-net-examples/facades-secure-documents/AGENTS.md

C# examples for facades-secure-documents using Aspose.PDF for .NET

aspose-pdfAGENTS.md

agentic-net-examples / securing-and-signing-pdf

aspose-pdf/agentic-net-examples/securing-and-signing-pdf/AGENTS.md

C# examples for securing-and-signing-pdf using Aspose.PDF for .NET

Nick2bad4uReads credentialsAGENTS.md

Github-Security-CodeScanning-Alerts-Skill

Nick2bad4u/Github-Security-CodeScanning-Alerts-Skill/AGENTS.md

Repository guidance for the GitHub security alerts management skill.

Nick2bad4uAGENTS.md

Github-Security-CodeScanning-Alerts-Skill / workflows

Nick2bad4u/Github-Security-CodeScanning-Alerts-Skill/.github/workflows/AGENTS.md

GitHub Actions guidance for the GitHub security alerts skill repository.

jrodrigopucaAGENTS.md

local-agents / security

jrodrigopuca/local-agents/security/AGENTS.md

Use this agent for DEFENSIVE security on your own code — threat modeling, adversarial code audit, and actionable remediation. Attacker mindset (Elliot Alderson archetype) pointed at hardening the product; the vulnerability is the adversary, never the developer.

morlutoAGENTS.md

rea

morluto/rea/AGENTS.md

cover finalization. Before adding complexity for a speculative or vanishingly unlikely race or security edge case, explain the concrete failure mode, likelihood, and complexity cost to the user

clawdbotAGENTS.md

clawdbot

clawdbot/clawdbot/AGENTS.md

incidents. No engineering for millisecond races, theoretical interleavings, or adversarial timing unless user data, security, or money at risk, or a real incident shows them. - Prefer cheap mechanisms: idempotency keys

moltbotAGENTS.md

moltbot

moltbot/moltbot/AGENTS.md

incidents. No engineering for millisecond races, theoretical interleavings, or adversarial timing unless user data, security, or money at risk, or a real incident shows them. - Prefer cheap mechanisms: idempotency keys

steipeteAGENTS.md

warelay

steipete/warelay/AGENTS.md

incidents. No engineering for millisecond races, theoretical interleavings, or adversarial timing unless user data, security, or money at risk, or a real incident shows them. - Prefer cheap mechanisms: idempotency keys

molt-botAGENTS.md

clawdbot

molt-bot/clawdbot/AGENTS.md

live authority. - Core owns shared message tools, action vocabulary, and dispatch; channels own account, security, conversation, and transport contracts. Keep typed command/approval/URL/action distinctions until encoding; never infer commands from

molt-botReads credentialsAGENTS.md

clawdbot / scripts

molt-bot/clawdbot/scripts/AGENTS.md

Manual or unverified cancellation remains refused. Branch-caused or unattributed failures, other required checks, security, and required reviews remain blocking. Exact-head `github_pending` preparation remains pending. GraphQL owns observations

DeepSeekReads credentialsAGENTS.md

deepseek-harness

deepseek-ai/deepseek-harness/AGENTS.md

DEFAULT_*` constant or test hook is not configurability. Protocol constants, external specs, and security invariants stay fixed. - **Misconfiguration fails loud** at load when self-contained, otherwise at the earliest resolvable

DeepSeekAGENTS.md

deepseek-harness / experimental

deepseek-ai/deepseek-harness/packages/experimental/AGENTS.md

packages through `devDependencies`; examples may load them explicitly. - Experimental status does not relax engineering, security, documentation, lifecycle, testing, or snapshot requirements. - Publishing an experimental package does not promote

No other project uses it yet

NousResearchReads credentialsAGENTS.md

hermes-agent

NousResearch/hermes-agent/AGENTS.md

contract tests; E2E with real imports against a temp `HERMES_HOME` for resolution, config, security and I/O changes; salvage by cherry-pick so authorship survives. **Rejected even when well-built

No other project uses it yet

NousResearchReads credentialsAGENTS.md

hermes-agent / hermes_cli

NousResearch/hermes-agent/hermes_cli/AGENTS.md

automatically. Top-level sections (non-exhaustive): `model, agent, terminal, compression, display, stt, tts, memory, security, delegation, smart_model_routing, checkpoints, auxiliary, curator, skills, gateway, logging, cron, profiles, plugins, honcho`. `auxiliary

NousResearchReads credentialsAGENTS.md

hermes-agent / skills

NousResearch/hermes-agent/skills/AGENTS.md

autonomous-ai-agents, blockchain, communication, creative, devops, email, health, mcp, migration, mlops, productivity, research, security, web-development`. Reviewing a skill PR: check the target directory — heavy-dep or niche skills

No other project uses it yet

affaan-mAGENTS.md

ECC

affaan-m/ECC/AGENTS.md

domain tasks 2. **Test-Driven** — Write tests before implementation, 80%+ coverage required 3. **Security-First** — Never compromise on security; validate all inputs 4. **Immutability** — Always create new objects, never mutate

No other project uses it yet