Secrets & credentials
529 rows from 274 repositories
Keys, tokens and keeping them out of the repository.
What Secrets & credentials skills agree on
217 skill files read, by 219 of the 226 authors on this shelf whose files we hold, 2026-09-06
The middle one of the 31 measured here is ~2.0k tokens long, counted with cl100k_base
Counted by distinct author, so one author publishing three of these counts once. Where a claim sits in fewer files than authors, that is said: a claim held by forty authors across three files is one file people copied, not forty people who agreed. Near-identical wordings are grouped and the other wordings are shown, so the grouping is yours to check.
What they tell the agent to do
- Rotate secrets regularly12 of 219 in 9 filesalso worded as Rotate secrets at least every 365 days
- Use different secrets per environment10 of 219 in 7 filesalso worded as use separate secrets per environment
- Mask secrets in logs10 of 219 in 7 filesalso worded as Mask secrets in logs and error messages
- Enable audit logging10 of 219 in 9 filesalso worded as enable secrets manager audit logging; enable Vault audit logging
- Encrypt secrets at rest9 of 219 in 6 files
- Use short-lived tokens when possible9 of 219 in 6 filesalso worded as Prefer short-lived tokens
- Rotate exposed credentials immediately9 of 219 in 6 filesalso worded as Rotate any found credential immediately, assume compromised; Rotate matched credentials immediately at the issuing service
- Use hierarchical numbering for numbered sequences9 of 219also worded as Use hierarchical numbering for sequential notes; Number notes hierarchically in numbered sequences
- Identify secret types, owners, and rotation requirements8 of 219 in 5 files
- Choose a secrets backend and access model8 of 219 in 5 files
- Validate rotation and audit logging8 of 219 in 5 files
- Document secret requirements8 of 219 in 5 files
- Install gitleaks as a pre-commit hook7 of 219 in 4 filesalso worded as Install gitleaks pre-commit hook in every repo; run gitleaks in pre-commit hooks
- Use index notes instead of folders6 of 219also worded as Organize with index notes instead of folders
- Rewrite git history with git-filter-repo6 of 219 in 3 filesalso worded as Remove secrets from git history with git filter-repo; rewrite history with git-filter-repo
What they tell it not to do
- Never commit secrets to source control13 of 219 in 10 filesalso worded as Never commit secrets to Git; Never commit secrets
- Never hardcode secrets in source code10 of 219 in 9 filesalso worded as Never hardcode secrets in source; Never hardcode secret literals in code
- Never bake secrets into images or config files8 of 219 in 6 filesalso worded as Never commit secrets or bake them into images; Never bake secrets into Docker image layers
- Do not use folders for organization8 of 219also worded as Do not use folders to organize notes; Do not create folders for organisation
- Never run store commands that print secrets7 of 219also worded as Never run store commands that print secrets; Never store secrets in source code or version control
- Never assume a historical secret is inactive without verification5 of 219 in 2 filesalso worded as never assume a historical secret is inactive
- Do not run git-filter-repo without team coordination5 of 219 in 2 filesalso worded as never run git-filter-repo without team coordination
- Do not scan running applications or container images5 of 219 in 2 filesalso worded as do not scan container images with gitleaks
- Do not use this for post-detection secret management5 of 219 in 2 filesalso worded as Do not use for managing secrets
- Never store API keys in plaintext5 of 219 in 3 filesalso worded as Never store keys in plaintext; never print keys in plaintext
What they expect to be installed
- grep29 of 219
- trufflehog23 of 219 in 19 files
- git22 of 219
- HashiCorp Vault18 of 219 in 15 files
- gitleaks17 of 219 in 14 files
- AWS Secrets Manager16 of 219 in 13 files
- External Secrets Operator13 of 219 in 10 files
- python313 of 219 in 10 files
- Azure Key Vault12 of 219 in 9 files
- vault12 of 219 in 9 files
What they ask it to produce
- Pre-commit secret scanning hook8 of 219 in 5 filesalso worded as pre-commit secret-scanning hook; pre-commit secret-scanning hooks
- Pre-commit hook configuration7 of 219 in 4 filesalso worded as Pre-commit config with gitleaks hook; pre-commit hook script
- CI secret scanning job7 of 219 in 4 filesalso worded as CI secret-scanning job; CI secret-scanning workflow
- Markdown notes with YAML frontmatter6 of 219also worded as Notes with YAML frontmatter including created date; Markdown note with YAML frontmatter
- Index notes listing wikilinks6 of 219also worded as Index note of wikilinks; Index notes containing wikilink lists
- JSON secret scan report5 of 219 in 2 filesalso worded as JSONL scan report
- Formatted secret scanning report5 of 219 in 2 filesalso worded as findings report in secret-scan format
- Secret requirements documentation5 of 219 in 4 filesalso worded as Documented secret requirements
When Secrets & credentials authors say to reach for one
The situations these authors wrote into their own files, counted out of the same 219 authors, with the skills that name each one
- Storing API keys and credentials10 of 219 in 7 files
- Secrets management
- Secrets management skills wshobson secrets management
- and 13 more on this shelf
- Rotating secrets automatically9 of 219 in 6 files
- Secrets management
- Secrets management skills wshobson secrets management
- and 13 more on this shelf
- User wants to find, create, or organize Obsidian notes9 of 219
- Obsidian vault
- and 13 more on this shelf
- Handling TLS certificates8 of 219 in 5 files
- Managing database passwords8 of 219 in 5 files
- Implementing least-privilege access7 of 219 in 4 files
How Secrets & credentials skills are built
475 skill directories by 239 authors, read from their repositories’ own file trees 2026-08-05
The middle bundle among those shipping files is 3 files, 20.2 KB beside SKILL.md
Counted by distinct author, same as above, so one author publishing forty template copies counts once. SKILL.md itself is not counted as a file, so a single-file skill is one where that file is the whole skill.
The shape
- SKILL.md is the whole skill109 of 239 authors, 208 of 475 skills
- files ship beside it130 of 239 authors, 267 of 475 skills
- executable scripts ship inside64 of 239 authors, 147 of 475 skills
The folders they converge on
- references/66 of 239 authors, 150 of 475 skills
- scripts/54 of 239 authors, 136 of 475 skills
- agents/17 of 239 authors, 21 of 475 skills
- assets/16 of 239 authors, 47 of 475 skills
- evals/10 of 239 authors, 13 of 475 skills
- templates/6 of 239 authors, 6 of 475 skills
MihaiBuilds/memory-vault/io.github.MihaiBuilds/memory-vault MCP server
60★ repoLocal-first AI memory layer with hybrid search. Postgres + pgvector. Self-hosted, MIT.
Perseus Vault (formerly Mimir/Mneme), persistent memory engine for AI agents
Perseus-Computing-LLC/perseus-vault/io.github.Perseus-Computing-LLC/perseus-vault MCP server
47★ repoPersistent, deterministic memory for AI agents. Local-first: SQLite, FTS5, AES-256-GCM, 55+ tools.
withqwerty/nutmeg/skills/acquire Skill
no license31★ repoFootball data analytics toolkit for Claude Code. Covers Opta, StatsBomb, Wyscout, SportMonks, and free sources.
pvliesdonk/markdown-vault-mcp/io.github.pvliesdonk/markdown-vault-mcp MCP server
27★ repoMarkdown vault MCP server with FTS5 + semantic search and frontmatter indexing
ChronoAIProject/Ornn/examples/api-fetch-wrapper Skill
19★ repoYour all-in-one skills-as-a-service platform to manage your skills, auto-generate skills and use agent skills as simple as calling an API.
aliasunder/vault-cortex/io.github.aliasunder/vault-cortex MCP server
17★ repoStandalone MCP server for Obsidian vaults — hybrid search, notes & files, memory, tasks, OAuth 2.1.
OleksandrKucherenko/mcp-obsidian-via-rest/io.github.OleksandrKucherenko/mcp-obsidian-via-rest MCP server
13★ repoAccess Obsidian vaults via Local REST API - read, search, and interact with notes
Pulse8 ai cortex knowledge vault
synpulse8-opensource/pulse8-ai-cortex-knowledge-vault/io.github.synpulse8-opensource/pulse8-ai-cortex-knowledge-vault MCP server
12★ repoAgent-native knowledge OS on Markdown: typed graph, hybrid search, and compiler over MCP.
mlorentedev/hive/io.github.mlorentedev/hive-vault MCP server
9★ repoOn-demand Obsidian vault access for AI coding assistants — 17 tools, 5 resources, 4 prompts.
jessepwj/vault-loop/skill/vault-loop Skill
8★ repoOpen-source prompt and Agent Skill for recurring knowledge-base update loops
jpmorgan-payments/pdp-skills/skills/jpm-integrations-get-started Skill
6★ repoAgent skills that give GitHub Copilot, Claude Code, and other AI coding assistants procedural knowledge of J.P. Morgan Payments APIs. Walks external developers from onboarding and credential setup through OAuth implementation and live API integration with Checkout and Online Payments.
rogerdigital/vault-inspector/skills/vault-inspector Skill
6★ repoAn Obsidian vault health checker for finding broken links, orphan attachments, duplicate files, frontmatter drift, stale tags, and large files.
Philidor DeFi Vault Risk Analytics
Philidor-Labs/philidor-mcp/io.philidor/defi-vaults MCP server
5★ repoSearch 700+ DeFi vaults, compare risk scores, analyze protocols. No API key needed.
benderterminal/zkettle Skill
3★Self-hosted, zero-knowledge encrypted, self-destructing secrets
aliasunder/agent-skills/skills/obsidian-vault Skill
3★ repoAgent skills for AI coding agents — trip planner, Obsidian vault, and more
generalbusiness-ai/keep-hermes-skills/skills/github/github-vault-search Skill
3★ repoSkills repository for Hermes agent
leo-cheung-itlger/api-key-leak-checker-leop/skills/api-key-leak-checker-leop Skill
3★ repoA Codex skill and pre-publish gate for checking API key leaks before open-sourcing projects.
graphlit/vault-sync/plugins/vault-sync/skills/vault-sync-setup Skill
2★ repoSync Vault Git repositories to local Markdown for Claude Code, Codex, OpenClaw, Cursor, and other file-aware AI agents.
scalekit-inc/skills/skills/adding-api-key-auth Skill
no license2★ repo35 skills that teach AI coding agents to integrate Scalekit auth — agent auth, full-stack login, MCP OAuth 2.1, enterprise SSO, and SCIM. Works with Claude Code, Cursor, Windsurf, and 35+ other agents.
jabez007/johnny-decimal-zettelkasten/.agents/skills/librarian-vault-manager Skill
no license2★ repoThis project is a compounding knowledge system ("Second Brain") that manages multiple Obsidian vaults, combining Johnny Decimal for structural organization with Zettelkasten for emergent meaning, augmented by AI librarian agents for maintenance.
1clawAI/1claw-mcp/io.github.1clawAI/1claw-mcp MCP server
2★ repoHSM-backed vault secrets for AI agents (JIT fetch) plus prompt-injection and threat scanning.
FastMCP server for surgical queries against a vault knowledge graph (NetworkX no
adelaidasofia/graph-query-mcp/io.github.adelaidasofia/graph-query-mcp MCP server
2★ repoFastMCP server for surgical queries against a vault knowledge graph (NetworkX node-link JSON).…
seburbina/skillhub/base-skill/skillhub-identity Skill
no license1★ repoAgent Skill Depot — public skills social network for Claude agents. Publish, discover, install, and rank Claude skills by how much work they offloaded. Cloudflare Workers + Neon + pgvector + R2.
hootbu/llm-wiki-mind/skills/vault-init Skill
1★ repoPersistent Obsidian wiki pattern for LLM agents: starter template + init script + Claude Code skills for continuous, cumulative knowledge archives.
AtlasPA/openclaw-vault Skill
no license1★Credential lifecycle security for OpenClaw workspaces. Audit exposure, inventory secrets, detect stale credentials. Free alert layer.
Freedomzyi/vault-keeper-zy Skill
no license1★🤖 AI 驱动的 Obsidian 知识库自动化管家 · Zettelkasten + PARA + 渐进摘要 · 零手动维护
Mahermenix/vault-sync Skill
1★Your project's second mind — a Claude Code skill that turns every session into structured, linked Obsidian notes your AI can reference.
Chill-AI-Space/vault-mcp/io.github.Chill-AI-Space/vault MCP server
1★ repoMCP server for credential isolation — bots use passwords and API keys without seeing them
RobThePCGuy/rag-vault/io.github.RobThePCGuy/rag-vault MCP server
no license1★ repoLocal RAG MCP server with hybrid search, PDF/DOCX support, and zero-config setup
Multi-workspace Slack MCP server with draft+confirm safety, vault auto-export, a
adelaidasofia/slack-mcp/io.github.adelaidasofia/slack-mcp MCP server
1★ repoMulti-workspace Slack MCP server with draft+confirm safety, vault auto-export, and triple-mode…
ericlovold/sanction/io.github.ericlovold/sanction MCP server
no license1★ repoAuthorize an AI agent's spend & credential use before it acts — budgets, encrypted vault, audit.
Runesmith-Studio/claude-vault Skill
0★Back up and migrate your Claude Code setup (~/.claude) safely across machines and accounts. Cross-platform, pure Python stdlib, MIT licensed.
tga-cheetung/account-intelligence-vault/.claude/skills/account-vault Skill
0★ repoOne markdown file per target account. Agents read it before every score, email, and call. Every signal compounds. Public Claude Code skill + heartbeat + per-account schema that mirrors your CRM.
Tyr0/agent-skills/plugins/credential-expert/skills/credential-storage Skill
0★ repoA collection of skills, plugins, and agents for AI workflows.
LinLin00000000/aiops-vault-template Skill
0★Local-first, agent-friendly AIOps vault template with Markdown/JSONL truth sources and thin companion skills.
scchearn/loam/skills/loam-ground/loam-initializing-vault Skill
0★ repoWorkflow skills for AI coding agents: plan, execute, and maintain a persistent knowledge base across sessions.
WIHATN/vault-crystallize Skill
no license0★Claude/agent skill for checkpointing progress into Handoff.md and distilling sources into a cited, confidence-rated evidence log inside an agent-managed knowledge vault.
CaptainTimmeow/creator-vault-skill/.agents/skills/creator-vault Skill
0★ repoCopy-only local media ingest for creators using a Codex skill
chang769/llm-wiki-vault-manager Skill
no license0★Agent skill for building source-backed LLM-wiki learning vaults for Codex and Claude Code
BWBlueVector/obsidian-vault-conventions Skill
0★Claude Code skill that keeps an AI's persistent memory correctly readable by both the AI and a human browsing it in Obsidian
nauta-ai/holster/com.nautaai/holster-mcp MCP server
0★ repoLocal-first secret scanning, rotation, vault, and audit-log tools for AI agents.
seanwinslow28/sw-mcp-vault-knowledge/com.seanwinslow/vault-knowledge MCP server
0★ repoRead-only MCP over a vault's typed knowledge graph: concept search, contradictions, article fetch.
AIWerk/mcp-server-vault/io.github.AIWerk/mcp-server-vault MCP server
0★ repoBitwarden/Vaultwarden for agents: list tagged items, TOTP codes, one-time Sends, save new secrets.
KN0WBOT/clavis-mcp/io.github.KN0WBOT/clavis MCP server
0★ repoEncrypted credential vault for AI agents — auto OAuth refresh, rate limiting, audit logging.
apilocker/apilocker/io.github.apilocker/apilocker MCP server
0★ repoEncrypted credential vault: LLM, service & OAuth keys. 21-tool MCP server for your AI agent.
bch1212/agentvault/io.github.bch1212/agentvault MCP server
0★ repoCredential vault for AI agents — Fernet-encrypted keys, per-agent budgets, audit logs.
ciinkwia/lithium-vault-mcp/io.github.ciinkwia/lithium-vault-mcp MCP server
0★ repoPrimary-source lithium & battery-metals mining data (AISC, reserves, filings) via x402.
ericm1018/skillfm-byok-vault-mcp/io.github.ericm1018/skillfm-byok-vault-api-key-provider-usage MCP server
0★ repoBYOK vault, provider API key guidance, usage visibility, and SkillFM Beacon checks for MCP agents.
mdfifty50-boop/secure-vault-mcp/io.github.mdfifty50-boop/secure-vault MCP server
no license0★ repoEncrypted secrets and credential management for agents
onetrueclaude-creator/hebbian-vault/io.github.onetrueclaude-creator/hebbian-vault MCP server
0★ repoUsage-adaptive Obsidian vault search: Hebbian + PageRank + BM25 hybrid ranking.
onetrueclaude-creator/vault-health-mcp/io.github.onetrueclaude-creator/vault-health-mcp MCP server
0★ repoObsidian vault structural health: broken links, orphans, missing frontmatter, safe auto-repair.
srotzin/hive-mcp-vault/io.github.srotzin/hive-mcp-vault MCP server
0★ repoA2A ZK wallet recovery — guardian swarm, no seed phrase, HiveLaw enforcement
genli-ai/market-research-skills/skills/local-vault Skill
59★ repoTurn Claude into a disciplined research analyst — verify facts against primary sources, brief any topic, draft flagship reports. Standalone or chained; runs across LLM terminals. | 把 Claude 变成讲纪律的研究分析师:核实事实、主题简报、旗舰研报,引用一手来源、绝不造数;可单用或串联,跨 LLM 终端。
timwukp/agent-skills-best-practice/skills/skills/agentcore-harness-builder Skill
7★ repo35 portable agent skills (Agent Skills spec) for Kiro & Claude Code: Scrum DevSecOps roles, PCI-DSS/MAS TRM compliance, AWS Well-Architected reviews — each with evals and a 4-layer tested methodology
ethanaubuchon/dossier-tradecraft/skills/capture-to-vault Skill
3★ repoClaude Code workflow recipes built on dossier-mcp — research → design → scope → decompose → implement as overridable slash commands and skills.
jayantak/vaultmem/skills/vault-capture Skill
3★ repoAgent memory over an Obsidian vault — bash + ripgrep, no database. A restricted-TOML vault registry, a curated Agent Index, a wikilink graph, and a Projects→Sessions lifecycle. Ships the vaultmem CLI + memory skills as a Claude Code plugin.
graphlit/vault-sync/plugins/vault-sync/skills/vault-sync-use Skill
2★ repoSync Vault Git repositories to local Markdown for Claude Code, Codex, OpenClaw, Cursor, and other file-aware AI agents.
mturac/hermes-supercode-skills/skills/auth-architect Skill
2★ repo⚡ 13 production-grade skills for Claude Code · db-whisperer, auth-architect, obs-guardian + 10 more · Zero config · MIT
jabez007/johnny-decimal-zettelkasten/.gemini/skills/librarian-vault-manager Skill
no license2★ repoThis project is a compounding knowledge system ("Second Brain") that manages multiple Obsidian vaults, combining Johnny Decimal for structural organization with Zettelkasten for emergent meaning, augmented by AI librarian agents for maintenance.
hootbu/llm-wiki-mind/skills/vault-lint Skill
1★ repoPersistent Obsidian wiki pattern for LLM agents: starter template + init script + Claude Code skills for continuous, cumulative knowledge archives.