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 skills add fakoli/fakoli-plugins --skill crew-opsgit clone --depth 1 https://github.com/fakoli/fakoli-pluginsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/fakoli/fakoli-plugins/crew-ops)<a href="https://agentmods.dev/skills/fakoli/fakoli-plugins/crew-ops"><img src="https://agentmods.dev/badge/skills/fakoli/fakoli-plugins/crew-ops/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/fakoli/fakoli-plugins/crew-ops"><img src="https://agentmods.dev/badge/skills/fakoli/fakoli-plugins/crew-ops.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00153 | $0.00899 |
| Opus 5.5 | $0.00061 | $0.00360 |
| Sonnet 5.5 | $0.00031 | $0.00180 |
| Haiku 4.5 | $0.00015 | $0.00090 |
Grade A, and why
crew-ops 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 1mo 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
In Codex, first read the native runtime adapter.
Crew Operations
To orchestrate multi-agent work, assign one owner per file, route work through the wave pattern below, and have each agent write status to the path the orchestrator provides in the dispatch prompt. The default scratch root is .fakoli/runs/<run-id>/; the orchestrator supplies the absolute path so agents remain path-agnostic.
Available Agents
See references/agent-roster.md for the full 9-agent roster with roles, colors, and file paths.
Pre-Built Crews
- Code quality: guido + critic + sentinel
- Plugin development: smith + guido + sentinel + herald
- Research & build: scout + guido + welder (critic as gate)
- Full overhaul: all 9 in waves
Companion Command
/crew — list all 9 agents and suggest crew compositions for a given task.
Related Skill
debugging — systematic 4-phase root cause analysis (see ../debugging/SKILL.md).
Wave Pattern
See references/wave-patterns.md for the full multi-wave protocol, including timing, hand-off rules, and gate criteria.
- Research: scout gathers information
- Build (parallel): guido + smith + herald create new artifacts
- ── CRITIC GATE ── critic reviews all modified files (non-negotiable)
- Integrate: welder wires it together
- ── CRITIC GATE ── critic reviews the integration
- Final Verification: sentinel produces evidence-based scorecard
- Infrastructure + Judge: keeper syncs infra, orchestrator reviews findings
Critic is a standing gate, not a wave agent. It fires after every wave that writes code.
Compressed 3-Wave Pattern (for smaller tasks)
For tasks with 1-5 file changes, collapse to 3 waves:
- Build (parallel): appropriate agents create/modify
- ── CRITIC GATE ── critic reviews
- Verify: sentinel validates
Use the full 5-wave pattern when >5 files change or multiple concerns overlap.
File Ownership
Each agent owns specific files. No two agents modify the same file. If overlap is needed, one agent is primary and the other coordinates via status files. See references/file-ownership.md for the full per-agent ownership matrix.
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/agent-roster.md 2.5 KB
- references/communication.md 7.1 KB
- references/critic-checklist.md 2.0 KB
- references/file-ownership.md 4.4 KB
- references/guido-style.md 21 KB
- references/iron-rule.md 2.1 KB
- references/python-style.md 48 KB
- references/rust-style.md 37 KB
- references/scout-template.md 2.0 KB
- references/wave-patterns.md 8.0 KB
- references/welder-patterns.md 36 KB
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.
- 1mo ago Changed · +3 lines b9a66bb4f225
- 1mo ago First seen · 71 lines · 153 tokens per session scan A e3d672853ead
crew-ops is a skill published in the GitHub repository fakoli/fakoli-plugins (4 stars, last pushed 27d ago), licensed MIT. It adds 153 tokens to every session and 899 once invoked, about $0.0006 per session on Opus 5.5. 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 skills, from other repositories
issue-triage
Use when the user wants to triage GitHub issues - decide whether an issue is still relevant, reproducible, closeable, a duplicate, or what concretely needs doing. Selects and prioritizes first (never dumps all issues at once), then deep-triages the chosen issues via parallel subagents, recommends actions for the owner…
requirements-verbatim
Capture a user requirement, decision, approval, or constraint word-for-word into an append-only dated log so it survives context compaction and can never be trimmed, softened, or reinterpreted. Use whenever the user states or approves a requirement, gives a GO, sets a constraint, or makes any decision that later work…
work-planning
Design the complete work hierarchy for a Paperclip company — Goals, Projects, and Tasks as a unified top-down planning workflow. Produces .planning.json for deterministic generation of goals/, projects/, and tasks/ directories. Use when creating a new company's work plan, reorganizing work structure, or linking goals…
project
A single starting point for setting up an AI-assisted project in Claude Cowork. It asks questions about the work, reviews available add-ons, and creates project instructions, custom agents, and connected workflows.
hr-operations
A skill for designing remote-work and team-operation policies. It covers flexible work, asynchronous communication, collaboration tools, productivity tracking, and employee experience.
hr-performance-review
A skill for designing and running employee performance reviews. It covers MBO, OKRs, KPIs, 360-degree feedback, review guides, and feedback conversations; OKRs set goals and measurable results, while KPIs track ongoing performance.