fabaindaiz/agents-knowledge
A portable .agents/ bundle for AI coding assistants
ARCHETYPE
Fort Knox
Deny lists, pre-tool hooks, sandboxing. Nothing touches prod without a signature.
GUARDRAILS
4/5
Blocks destructive commands · Pre-tool screening hook · No YOLO mode · Sandbox or ask-first rules · details
Copy this rig
# review before running: this installs third-party code
$ npx degit fabaindaiz/agents-knowledge/.claude ./rig-agents-knowledge # inspect, then merge into .claude/ MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit fabaindaiz/agents-knowledge/.agents/method/skills/close .claude/skills/close $ npx degit fabaindaiz/agents-knowledge/.agents/method/skills/decision-review .claude/skills/decision-review $ npx degit fabaindaiz/agents-knowledge/.agents/method/skills/next .claude/skills/next $ npx degit fabaindaiz/agents-knowledge/.agents/method/skills/user-walk .claude/skills/user-walk
$ curl -fsSL --create-dirs -o .claude/agents/knowledge-reviewer.md https://raw.githubusercontent.com/fabaindaiz/agents-knowledge/main/.claude/agents/knowledge-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/researcher.md https://raw.githubusercontent.com/fabaindaiz/agents-knowledge/main/.claude/agents/researcher.md
Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.
{
"permissions": {
"deny": [
"Edit(/.agents/SHA256SUMS)"
],
"ask": [
"Edit(/.claude/hooks/**)",
"Edit(/.claude/settings.json)",
"Edit(/.githooks/**)",
"Edit(/.agents/tools/**)",
"Edit(/.agents/agents/**)",
"Edit(/.agents/method/**)",
"Edit(/.agents/knowledge/**)",
"Edit(/.agents/README.md)",
"Edit(/.agents/CHANGELOG.md)",
"Edit(/.agents/proposals/README.md)",
"Edit(/.agents/proposals/RECEIVED.md)",
"Edit(/.claude/skills/*/SKILL.md)",
"Edit(/.claude/agents/**)"
]
},
"hooks": {
"PreToolUse": [
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": "python3 \"$CLAUDE_PROJECT_DIR/.claude/hooks/privacy_guard.py\" gate"
}
]
}
]
}
} Skills (4)
Subagents (2)
| knowledge-reviewer | Reviews a diff against the engineering knowledge in .agents/knowledge/ (topics: distributed-correctness, failure-behaviour, evolving-contracts, time-and-control, adversarial-controls, identity-and-nam |
| researcher model: sonnet | Answers a research question from primary sources on a cheaper model, reading only; reports each claim with its source. Use for delegated research. |
Hooks (2)
| event | matcher | runs |
|---|---|---|
| SessionStart | * | python3 "$CLAUDE_PROJECT_DIR/.claude/hooks/privacy_guard.py" remind |
| PreToolUse | Bash | python3 "$CLAUDE_PROJECT_DIR/.claude/hooks/privacy_guard.py" gate |
Permissions
deny (1)
Edit(/.agents/SHA256SUMS)
ask (13)
Edit(/.claude/hooks/**)
Edit(/.claude/settings.json)
Edit(/.githooks/**)
Edit(/.agents/tools/**)
Edit(/.agents/agents/**)
Edit(/.agents/method/**)
Edit(/.agents/knowledge/**)
Edit(/.agents/README.md)
Edit(/.agents/CHANGELOG.md)
Edit(/.agents/proposals/README.md)
Edit(/.agents/proposals/RECEIVED.md)
Edit(/.claude/skills/*/SKILL.md)
Edit(/.claude/agents/**)
allow (0)
—
Similar rigs
haoblackj/dotfiles
haoblackj's dotfiles
Pragmatist 3.4k tok ·
jaqubowsky/fleet
Runs Claude Code and pi agents in parallel on your Mac, one Docker sandbox per issue. A host agent hands out the work, watches every sandbox and brings back tested, reviewed pull requests.
Minimalist 341 tok ·
ychampion/claude-self-learning
A Claude Code self learning plugin that autonomously researches any technology and generates reusable SKILL.md files with installation guides, code examples, and best practices.
Pragmatist 252 tok ·
syntax-syndicate/cc-solo-dev-template
Claude Code Solo Development Workflow Template - Ship like a team of 10, working solo with AI agents
Minimalist 660 tok ·