agentleFS

Find the best CLAUDE.md, AGENTS.md and Claude skills

One search for your own team's files and the public ecosystem. See how real projects write their agent instructions, and bring the good ideas home.

Best matches · from page 20Worked for most · soon
kcns008Pipes a download into a shellSkill

k8s-security

kcns008/cluster-skills/.claude/skills/k8s-security/SKILL.md

Kubernetes and OpenShift security assessment, hardening, and compliance. Use this skill when: (1) Auditing cluster or workload security posture (2) Implementing Pod Security Standards/Admission (3) Configuring RBAC roles and permissions (4) Setting up NetworkPolicies for zero-trust (5) Managing Secrets securely (encryption, external secrets) (6) Scanning images for vulnerabilities (7) Implementing OCP SecurityContextConstraints (8) Compliance checking (CIS benchmarks, SOC2, PCI-DSS) (9) Security incident investigation (10) Hardening cluster components

410mo agoReviewMountCreate a free account to mount
langbyyiSkill

api-security

langbyyi/websec-skills/api-security/SKILL.md

Entry P1 category router for API security. Use when choosing between API recon, authorization, token abuse, and hidden-parameter workflows before any deeper API topic skill.

Often used withsrc-hunterpentest-toolsllm-security

45mo agoReviewMountCreate a free account to mount
lxsmnsycSkill

security-fix

lxsmnsyc/agent-skills/skills/security-fix/SKILL.md

Fix a security vulnerability without leaking it before the release. Work happens on a local-only branch that is never pushed, then merges straight into the branch the release workflow publishes from. The fix becomes public at the same moment CI publishes the release, so the package keeps npm provenance. Use this skill whenever the user asks to fix a security issue, vulnerability, advisory, CVE or GHSA, or when other work finds one, even if they do not say "security-fix".

418d agoReviewMountCreate a free account to mount
MBrekhofSkill

xaf-security

MBrekhof/xafskills/skills/xaf-security/SKILL.md

Configure DevExpress XAF security: roles, permissions, users, and background job authentication. Use when setting up role permissions in Updater.cs, implementing object-level security, exporting/importing roles, creating background job security contexts, or troubleshooting permission issues. Covers type-level vs object-level permissions, CurrentUserIdOperator, PermissionsReloadMode, and the role update caveat.

46mo agoReviewMountCreate a free account to mount
ryankoleanReads credentialsSkill

site-security

ryankolean/summit-claude-skills/skills/site-security/SKILL.md

Security scanning, evaluation, audit, resolution and monitoring for Summit websites and apps. Runs secrets, dependency, static-analysis, CI-workflow, header/TLS and live-site checks; normalizes every result into one findings file; gates production deploys; then triages findings and fixes them one atomic PR at a time. Activates on "security scan", "security audit", "is this site secure", "check for secrets", "vulnerability scan", "harden this site", "fix security findings", "security gate", "pre-launch security check", or as the security part of the framework's audit, launch gate (SUMMIT-252) and monitor modes.

47mo agoReviewMountCreate a free account to mount
secureIO-GmbHReads credentialsSkill

security-scan

secureIO-GmbH/security-skills/skills/security-scan/SKILL.md

Use this skill to run a security scan combining SAST analysis, secret/credential detection, dependency vulnerability scanning (SCA), and container/IaC misconfiguration checks on staged code or the full codebase. Invoke as `/security-scan` to scan only git-staged files (fast, pre-commit use), or `/security-scan full` to scan the entire codebase. Uses semgrep or opengrep for SAST, trufflehog for secrets, and trivy (preferred) or grype for SCA and container/IaC scanning. Validates and deduplicates findings, generates a structured markdown report with severity ratings, and offers to auto-remediate fixable issues. Trigger this skill whenever the user wants to: run a security scan, check for secrets or credentials in code, scan dependencies for CVEs, check container or IaC configuration, do a SAST scan before committing, scan for vulnerabilities, run semgrep, trufflehog, trivy, or grype, or get a security report on their code.

Often used withdjango-securitydeployment-patternspostgres-patterns

48mo agoReviewMountCreate a free account to mount
WishmakingfairySkill

security-scan

Wishmakingfairy/vibecheck/skills/security-scan/SKILL.md

This skill should be used when the user asks to \"run a security scan\", \"check for vulnerabilities\", \"security audit\", \"ship secure\", \"vibecheck scan\", or \"pre-deploy security check\". Runs 156 automated security checks across 15 categories and produces a categorized vulnerability report.

Often used withdjango-securitydeployment-patternspostgres-patterns

48mo agoReviewMountCreate a free account to mount
borgbaseDeletes or force-pushesSkill

security-review

borgbase/vykar/.agents/skills/security-review/SKILL.md

Security review skill for the vykar backup tool (Rust). Use when reviewing code for security issues, auditing cryptographic implementations, checking for credential leaks, reviewing unsafe code, or validating the security model of the backup tool. Covers encryption, key management, repository integrity, hook execution, config parsing, dependency auditing, and backup-specific attack surfaces.

Often used withdependency-cve-sweeplinkerd-patternsproject-guidelines-example

7263d agoReviewMountCreate a free account to mount
OneByJorahReads credentialsSkill

security-scrub

OneByJorah/offivo/.agents/skills/security-scrub/SKILL.md

Find and remove secrets, real hostnames, IPs, credentials, and private data from a repo before publishing. Use before any public release, screenshot commit, or README update.

2431d agoReviewMountCreate a free account to mount
ktnytSkill

security-review

ktnyt/cclsp/.claude/skills/security-review/SKILL.md

Request a security expert assessment for code changes that touch child process spawning, file system access, configuration loading, or environment variable handling. Use when the Reviewer identifies security-sensitive changes in the MCP-LSP bridge.

Often used withdependency-cve-sweeplinkerd-patternsproject-guidelines-example

6739mo agoReviewMountCreate a free account to mount
striderZASkill

security-audit

striderZA/OpenCodeGameStudios/.agents/skills/security-audit/SKILL.md

Audit the game for security vulnerabilities: save tampering, cheat vectors, network exploits, data exposure, and input validation gaps. Produces a prioritised security report with remediation guidance. Run before any public release or multiplayer launch.

Often used withcreate-storiesteam-coordinationcommunity-led-growth

12413d agoReviewMountCreate a free account to mount
deadlock-mod-managerReads credentialsSkill

security-review

deadlock-mod-manager/deadlock-mod-manager/.agents/skills/security-review/SKILL.md

Security code review for Tauri/Rust/TypeScript desktop apps and Hono/oRPC APIs. Use when asked to "security review", "find vulnerabilities", "check for security issues", "audit security", or review code for injection, XSS, IPC abuse, path traversal, or authentication issues. Provides confidence-based reporting tuned to the Deadlock Mod Manager stack.

Often used withdependency-cve-sweeplinkerd-patternsproject-guidelines-example

6172d agoReviewMountCreate a free account to mount
TheBeardedBearSASSkill

security-react

TheBeardedBearSAS/claude-craft/.claude/skills/security-react/SKILL.md

Sécurité React. Use when reviewing security, implementing auth, or hardening code.

1087d agoReviewMountCreate a free account to mount
full-stack-skillsSkill

tauri-security

full-stack-skills/tauri-skills/skills/tauri-security/SKILL.md

Guidance for Tauri v2 capabilities, scope configuration, and ACL-based permission control.

2059d agoReviewMountCreate a free account to mount
MystenLabsSkill

move-security

MystenLabs/skills/move-security/SKILL.md

Move smart contract security on Sui. Use when reviewing Move code for security vulnerabilities, designing access control patterns, handling capabilities safely, securing randomness usage, validating invariants, planning upgrade governance, managing keys, or auditing privileged operations. Also use when the user asks about UpgradeCap security, capability revocation, shared object authorization, onchain randomness restrictions, oracle data validation, emergency controls, or frontend transaction signing safety.

2020d agoReviewMountCreate a free account to mount
arsudsandesh97Skill

security-doc

arsudsandesh97/Revoact/skills/security-doc/SKILL.md

Generate a complete SECURITY.md file for any software project. Use whenever the user asks to create, write, generate, or draft a SECURITY.md — a comprehensive security documentation covering threat models, security controls, authentication, authorization, data protection, compliance requirements, and security best practices.

34mo agoReviewMountCreate a free account to mount
chadixearthReads credentialsSkill

security-scan

chadixearth/graphyloop/skills/security-scan/SKILL.md

Scan your OpenCode configuration (.opencode/ directory) for security vulnerabilities, misconfigurations, and injection risks using AgentShield. Checks AGENTS.md, settings.json, MCP servers, hooks, and agent definitions.

Often used withdjango-securitydeployment-patternspostgres-patterns

316d agoReviewMountCreate a free account to mount
CLAUDE.md vs AGENTS.md

Agent instruction files

What are agent instruction files?

Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.

CLAUDE.md or AGENTS.md?

CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.

What is a skill?

A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.

Can I search my own team's files too?

Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.