Security instructions files

1,250 tagged Security, measured the same way as everything else here.

Browse within: ai-security 65model-context-protocol 62cybersecurity 57copilot 40devsecops 40ai-tools 36AI Safety 33appsec 27bug-bounty 27claude-code-plugin 26code-quality 23compliance 22agent-security 20ai-coding 18

draugr CLAUDE.md

434

draugr-dev/draugr

Instructions file

Claude Code instructions for draugr-dev/draugr, covering working on draugr, what draugr is, layout, before you open a pr and design principles.

not rated 4 yesterday A 2,807 tokens original Apache-2.0

kdbx AGENTS.md

435

yarrasys/kdbx

Instructions file CodexOpenCode

AGENTS.md instructions for yarrasys/kdbx, covering agents.md, what this is, current status — read this first, golden rules and repository map.

not rated 4 yesterday B 3,066 tokens original MIT

Parselbox CLAUDE.md

436

thesanjeetc/Parselbox

Instructions file

Instructions for thesanjeetc/Parselbox, covering claude.md, architecture (host ↔ sandbox), commands, gotchas (learned the hard way) and conventions.

not rated 4 7d ago A 987 tokens original MIT

xAmirHamza77/ReverseOps-Skill

Instructions file

Claude Code instructions for xAmirHamza77/ReverseOps-Skill, covering claude.md, on any task, first-run setup, windows and macos / linux.

not rated 4 1mo ago A 341 tokens copy · 91% MIT

MCPAudit AGENTS.md

438

saagpatel/MCPAudit

Instructions file CodexOpenCode

AGENTS.md instructions for saagpatel/MCPAudit, covering agents.md, what this project is, current state, stack and how to run.

not rated 4 2d ago A 802 tokens original MIT

n-shadloo/secure-code-auditor

Instructions file CodexOpenCode

AGENTS.md instructions for n-shadloo/secure-code-auditor, covering agents.md, what this skill does, two modes, how to use the content and tool-specific entry points.

not rated 4 yesterday A 996 tokens original MIT

ai-appsec AGENTS.md

440

subodhkc/ai-appsec

Instructions file CodexOpenCode

Instructions for subodhkc/ai-appsec, covering agents.md — haiec agent security mcp (phase -1 → phase 18), 1. workspace layout, 2. architectural principles (apply to every phase), 3. hard constraints (never violate) and 4. phase discipline.

not rated 4 15d ago A 2,730 tokens original MIT

oh-my-vul AGENTS.md

441

bx33661/oh-my-vul

Instructions file CodexOpenCode

Instructions for bx33661/oh-my-vul, covering repository guidance, purpose, layout, development and conventions.

not rated 4 16d ago A 449 tokens original MIT

agentmessaging/agent-identity

Instructions file

Instructions for agentmessaging/agent-identity, covering claude.md, what this repo is, common commands, run any command directly from the repo without installing and architecture.

not rated 4 1mo ago E 2,551 tokens original MIT

ch015/code-pentester

Instructions file

Instructions for ch015/code-pentester, covering claude.md — ch015-pentester, reasoning discipline, project operational rules and tone.

not rated 4 17d ago A 480 tokens original MIT

froggeric/claude-smart-approval

Instructions file

Instructions for froggeric/claude-smart-approval, covering claude.md, project, commands, run all tests (requires bats, shfmt, jq) and run a single test file.

not rated 4 15d ago D 2,160 tokens original MIT

accessflow CLAUDE.md

446

bablsoft/accessflow

Instructions file

Claude Code instructions for bablsoft/accessflow, covering claude.md — accessflow agent rules, project at a glance, repository layout, backend and runtime & framework versions.

not rated 4 changed yesterday B 12,982 tokens original Apache-2.0

sgharlow/ai-control-framework

Instructions file

Instructions for sgharlow/ai-control-framework, covering claude code configuration, framework status (v2.0) — verified 2026-07-18, ⚠️ critical: implementation required, mandatory session start procedure and hard stop conditions.

not rated 4 1mo ago A 1,577 tokens original MIT

EnigmAgent AGENTS.md

448

Agnuxo1/EnigmAgent

Instructions file CodexOpenCode

Instructions for Agnuxo1/EnigmAgent, covering agents.md — enigmagent, what this is, how agents should use this repository, security & integration rules for agents and companion projects.

not rated 4 3mo ago A 945 tokens original MIT

kismatkunwar89/SAVVYDFIR-MCP

Instructions file

Instructions for kismatkunwar89/SAVVYDFIR-MCP, covering savvydfir-mcp - dfir investigation framework, what this is, critical rules, forensic knowledge in tool responses and investigation workflow (7 phases).

not rated 4 2mo ago A 10,844 tokens original MIT

BashaarJavaid/MCP-Sentinel

Instructions file CodexOpenCode

AGENTS.md instructions for BashaarJavaid/MCP-Sentinel, covering agents.md, project, where things live, conventions and commands.

not rated 3 changed today A 2,438 tokens original MIT

tool-gates CLAUDE.md

451

camjac251/tool-gates

Instructions file

Claude Code instructions for camjac251/tool-gates, covering tool gates maintainer guide, start here, repository map, commands and source-of-truth invariants.

not rated 4 today A 2,047 tokens

mitre-mcp AGENTS.md

452

lidless-labs/mitre-mcp

Instructions file CodexOpenCode

Instructions for lidless-labs/mitre-mcp, covering repository guidance, definition of done, project shape, verification workflow and soc safety (hard prohibitions).

not rated 4 27d ago A 1,139 tokens original MIT

ysfAskri/archguardian

Instructions file GitHub Copilot

Instructions for ysfAskri/archguardian, covering archguardian, project structure, build & test, key conventions and cli commands.

not rated 4 6mo ago A 752 tokens original MIT

patrick-oculussec/fedramp-ksi-agent-skills

Instructions file CodexOpenCode

Instructions for patrick-oculussec/fedramp-ksi-agent-skills, covering fedramp 20x compliance agent instructions, how to use these instructions, instruction sets by topic, cross-cutting requirements and complete ksi reference.

not rated 4 4mo ago A 877 tokens original MIT

sec-kit CLAUDE.md

455

segraef/sec-kit

Instructions file

Claude Code instructions for segraef/sec-kit, covering ai agent guardrails, secrets and credentials, untrusted input, running code and commits.

not rated 4 today C 574 tokens original MIT

rmyndharis/aimhooman

Instructions file GitHub Copilot

Instructions for rmyndharis/aimhooman: This repository uses aimhooman to keep AI tooling artifacts out of Git history. Its policy.

not rated 4 23d ago C 828 tokens original MIT