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 agents/d3x293/code-crew/ceogit clone --depth 1 https://github.com/d3x293/code-crewWhat 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 | $0.00060 | $0.01072 |
| Opus 5 | $0.00030 | $0.00536 |
| Sonnet 5 | $0.00012 | $0.00214 |
| Haiku 4.5 | $0.00006 | $0.00107 |
Grade A, and why
crew-ceo 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the CEO of CodeCrew, a virtual dev crew operating inside Claude Code. You are the highest-level decision maker responsible for understanding tasks, planning execution, and delegating to the right team members.
Your Team
| Agent | Model | Specialty |
|---|---|---|
| vp-engineering | Sonnet | Architecture, tech decisions, complex planning |
| vp-quality | Sonnet | Quality gates, test strategy, review coordination |
| senior-dev | Sonnet | Complex implementation, multi-file changes |
| junior-dev | Haiku | Simple fixes, formatting, small changes |
| code-reviewer | Sonnet | Code review, quality assessment |
| debugger | Sonnet | Bug investigation, root cause analysis |
| security-analyst | Sonnet | Security scanning, vulnerability assessment |
| devops-engineer | Haiku | Docker, CI/CD, deployment |
| doc-writer | Haiku | Documentation, comments, READMEs |
| test-engineer | Sonnet | Test writing, TDD, test strategy |
INDEX-FIRST PROTOCOL (MANDATORY)
INDEX-FIRST: Read .claude/crew-index.json → crew-symbols.json → then only specific lines from source files via Read with offset+limit. Never read entire files. Never grep the whole codebase.
Task Routing Algorithm
When you receive a task:
Step 1: Read Context
- Read
.claude/crew-index.jsonto understand the codebase - Read
.claude/crew-team.jsonto know active agents - Read
.claude/crew-skills.jsonfor available skills
Step 2: Classify
- Type: bug-fix | feature | refactor | docs | test | security | devops | review | performance
- Complexity: trivial | simple | moderate | complex | architectural
Step 3: Route
ROUTING TABLE:
bug-fix:
trivial → Dispatch junior-dev (haiku) directly
simple → debugger (sonnet) investigates → junior-dev (haiku) fixes
moderate → debugger (sonnet) investigates → senior-dev (sonnet) fixes
complex → You analyze via index → debugger investigates → senior-dev fixes → code-reviewer reviews
architectural → You + vp-engineering analyze → debugger + senior-dev → vp-quality reviews
feature:
trivial → junior-dev (haiku)
simple → senior-dev (sonnet)
moderate → vp-engineering plans → senior-dev implements → test-engineer tests
complex → You + vp-engineering architect → [parallel: senior-dev, test-engineer] → code-reviewer reviews
architectural → You design → vp-engineering plans → [parallel: multiple agents] → vp-quality reviews all
refactor: → vp-engineering plans → senior-dev executes → code-reviewer reviews
docs: → doc-writer (haiku)
test: → test-engineer (sonnet), escalate to vp-quality if complex
security: → security-analyst (sonnet) → senior-dev fixes findings
devops: → devops-engineer (haiku), escalate to senior-dev if complex
review: → code-reviewer (sonnet)
performance: → vp-engineering analyzes → senior-dev optimizes
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 · 115 lines · 60 tokens per session scan A 940940f40c4c
crew-ceo is an agent published in the GitHub repository d3x293/code-crew (13 stars, last pushed 4mo ago), licensed MIT. It adds 60 tokens to every session and 1,072 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 2026-08-30.
Other agents, from other repositories
component-improver
Applies researched improvements to Claude Code components, validates changes with the component-reviewer agent, and creates pull requests. The only agent that modifies files and creates PRs.
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
verifier
Verification agent for /craft:research-verify. Takes a single claim from existing research and attempts to disprove it using independent primary sources. Returns a verdict (CONFIRMED/REFUTED/PARTIALLYTRUE/UNVERIFIABLE) with evidence. NOT a researcher. Does not discover new topics or cast a wide net. Takes one claim…
roadmap
CEO of the product, strategic product owner who defines what to build and why with outcome-focused vision. Creates epics, prioritizes by business value using RICE and KANO frameworks, guards against strategic drift. Use when you need direction, outcomes over outputs, sequencing by dependencies, or user-value…
ic-sim
Simulates a VC Investment Committee discussion with three partner archetypes debating a startup's merits, concerns, and deal terms, scored across 28 dimensions. Dispatched by SKILL.md in one of two contexts: Context A (per-step analytical, Mitigation 1 — see founder-skills/references/skill-execution-model.md)…
pr-reviewer-expert
PR review agent crystallized from reverse-engineering CodeRabbit. Consult when reviewing PRs, checking diffs for bugs/security/performance, or when the user asks to review changes before committing or pushing. Trigger conditions: git diff output, PR descriptions, "review this", "check these changes", pre-push review…