Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/fakoli/fakoli-plugins/crewgit clone --depth 1 https://github.com/fakoli/fakoli-pluginsWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00052 | $0.00807 |
| Opus 5 | $0.00026 | $0.00404 |
| Sonnet 5 | $0.00010 | $0.00161 |
| Haiku 4.5 | $0.00005 | $0.00081 |
Grade A, and why
crew scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
List all 9 fakoli-crew agents with their roles, then suggest crew compositions for the user's current task (passed as the command argument, if any).
For deeper orchestration — wave patterns, file ownership, status-file protocol — invoke the crew-ops skill (triggers: "assemble a crew for…", "coordinate agents to…").
All Agents
See skills/crew-ops/references/agent-roster.md for the canonical 9-agent roster (names, colors, roles, and file paths).
Pre-Built Crews
Code Quality
Agents: guido + critic + sentinel (+ warden when the change touches auth, input handling, dependencies, or plugin permissions) Use when: You want to audit and improve an existing codebase.
1. critic audits — finds issues, assigns severity
2. guido rewrites — fixes MUST and SHOULD items with idiomatic TypeScript alternatives
3. sentinel validates — runs tests, confirms nothing regressed
Plugin Development
Agents: smith + guido + sentinel + herald Use when: Building a new plugin or adding major features to an existing one.
Wave 1: scout (research existing patterns)
Wave 2: smith (manifest) + guido (code)
Wave 3: sentinel (validate) + herald (README)
Research & Build
Agents: scout + guido + welder (critic as gate) Use when: Integrating an external library or API you haven't used before.
Wave 1: scout (read the docs, map the API)
Wave 2: guido (design the wrapper/interface)
── CRITIC GATE ──
Wave 3: welder (wire into existing code)
── CRITIC GATE ──
Documentation Sprint
Agents: herald + keeper + sentinel Use when: Docs are stale, READMEs are generic, or the registry is out of sync.
Wave 1: herald (rewrite READMEs with specific value propositions)
── CRITIC GATE ──
Wave 2: keeper (sync CLAUDE.md, marketplace.json, registry)
Wave 3: sentinel (verify counts match, links resolve)
Full Overhaul
Agents: All 9 in waves (critic as standing gate, warden as security gate) Use when: Major version bump, structural refactor, or preparing for public launch.
Wave 1: scout (research)
Wave 2 (parallel): guido + smith + herald (build)
── CRITIC GATE ──
Wave 3: welder (integrate)
── CRITIC GATE ──
Wave 4 (parallel): sentinel (final verification) + warden (security audit)
Wave 5: keeper (infrastructure) + orchestrator reviews findings
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 83 lines · 52 tokens per session scan A 142af9096ba8
crew is a command published in the GitHub repository fakoli/fakoli-plugins (4 stars, last pushed 24d ago), licensed MIT. It adds 52 tokens to every session and 807 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
session-init
You are the Main Agent in an orchestrated workflow. Read and internalize these working instructions.
permissions
Create or update DOGMA-PERMISSIONS.md to configure what Claude can do autonomously.
role-clear
Clear the persistent, per-session credo ROLE, returning to the default of NO role: the agent does everything, as it does when no role is set.
conjure-agent
Creates or updates a Claude Code agent definition (/.claude/agents/ .md or project-local).
conjure-hook
Create or update a Claude Code hook (settings.json entry + shell script). Provide a description of what you want the hook to do.
conjure
Use when you want to build a new Claude Code skill, agent, hook, or MCP server but aren't sure which — or when you want to describe what you want in plain language. Auto-detects the right artifact type, asks targeted questions, explains the reasoning, then builds it.