claude-skills is a large collection of reusable skills, commands, plugins, and supporting resources for coding agents across engineering, business, research, compliance, and productivity work. It is used by people who want agents such as Claude Code, Codex, Gemini CLI, or Cursor to follow specialized workflows. The catalogue contains selected skills and settings from the collection.
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.
git clone --depth 1 https://github.com/alirezarezvani/claude-skillsWrote 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/commands/alirezarezvani/claude-skills/cs-grill-bizops)<a href="https://agentmods.dev/commands/alirezarezvani/claude-skills/cs-grill-bizops"><img src="https://agentmods.dev/badge/commands/alirezarezvani/claude-skills/cs-grill-bizops/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/commands/alirezarezvani/claude-skills/cs-grill-bizops"><img src="https://agentmods.dev/badge/commands/alirezarezvani/claude-skills/cs-grill-bizops.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 | $0.00084 | $0.00921 |
| Opus 5.5 | $0.00034 | $0.00368 |
| Sonnet 5.5 | $0.00017 | $0.00184 |
| Haiku 4.5 | $0.00008 | $0.00092 |
Grade A, and why
cs-grill-bizops 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 today.
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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/cs-grill-bizops — BizOps grill against the canon
Apply Matt Pocock's grill-with-docs discipline to this BizOps plan / problem:
$ARGUMENTS
Five rules (preserved from Matt Pocock, MIT)
- One question per turn. Never bundle.
- Recommend an answer with each question. Defaulting to "what do you think?" is lazy.
- Explore the workspace before asking. If
Glob/Read/Grepresolves it, do that first. - Walk the decision tree depth-first. Finish a branch before opening another.
- Track dependencies. Resolve A before B if B depends on A.
The BizOps decision tree (depth-first)
Walk these branches in order. Skip a branch only if the workspace already resolves it.
Branch 1 — Which lane?
- PROCESS / VENDOR / CAPACITY / COMMS / KNOWLEDGE / PROCUREMENT
- Canon source: this skill's signal table +
references/per lane
Branch 2 — Measurement state
For PROCESS: "Do you have measured cycle times per stage, or estimates?" — Recommended: insist on measured for top-3 longest stages. Anti-pattern (Goldratt 1984): map estimates → optimize wrong constraint.
For VENDOR: "Tier-1 threshold — spend or operational dependency?" — Recommended: operational dependency. Anti-pattern (Target/HVAC breach, Verkada): spend-only tiering misses critical low-spend vendors.
For CAPACITY: "Plan for utilization or throughput?" — Recommended: throughput (Little's Law). Anti-pattern (DORA): planning for utilization > 80% destroys throughput.
For COMMS: "Push or pull comms?" — Recommended: depends on change magnitude. ADKAR model (Hiatt 2006): high-uncertainty change needs push + 7+ touchpoints.
For KNOWLEDGE: "SOP or runbook?" — Recommended: SOP if humans, runbook if 50% automated. Atlassian/Google SRE distinction.
For PROCUREMENT: "Spend or supplier consolidation goal?" — Recommended: consolidation if Pareto says top-20% suppliers = 80% spend. Else spend categorization.
Branch 3 — Owner + accountability
"Who owns this when the recommendation lands?" — Recommended: named human, not a team. Anti-pattern: 'the ops team owns it' = no one owns it.
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.
- today First seen · 75 lines · 84 tokens per session scan A 2c67966c7bb5
cs-grill-bizops is a command published in the GitHub repository alirezarezvani/claude-skills (28,607 stars, last pushed yesterday), licensed MIT. It adds 84 tokens to every session and 921 once invoked, about $0.0003 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 2026-10-24.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.
speckit.bug.test
Validate that a previously fixed bug is resolved and record the verification report.