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/kevinzai/commander/ccc-improve-commandsgit clone --depth 1 https://github.com/KevinZai/commanderWrote 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/kevinzai/commander/ccc-improve-commands)<a href="https://agentmods.dev/commands/kevinzai/commander/ccc-improve-commands"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc-improve-commands.svg" alt="Measured on agentmods" 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 | $0.00024 | $0.00483 |
| Opus 5 | $0.00012 | $0.00242 |
| Sonnet 5 | $0.00005 | $0.00097 |
| Haiku 4.5 | $0.00002 | $0.00048 |
Grade A, and why
ccc-improve-commands 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 yesterday.
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.
What it actually says
Improve Commands — Command Library Audit
Perform a comprehensive audit of all slash commands in ~/.claude/commands/.
Step 1: Inventory
List all command files with:
- File name
- Description (from frontmatter)
- Last modified date
- Line count (complexity indicator)
Step 2: Quality Check
For each command, evaluate:
- Clarity: Is the description clear? Does the name match what it does?
- Completeness: Does it cover all steps needed?
- Output format: Does it define a structured output?
- Edge cases: Does it handle when things go wrong?
- Freshness: Is it still relevant to current workflows?
Step 3: Gap Analysis
Check if these essential categories are covered:
- Code review / quality gate
- Testing (generation, TDD, coverage)
- Deployment (check, deploy, rollback)
- Debugging (session, investigation)
- Feature workflow (start, plan, ship)
- Documentation (generate, update)
- Git operations (checkpoint, commit, PR)
- Session management (save, resume, compact)
- Team coordination (peers, spawn, status)
- Project setup (init, configure)
Step 4: Recommendations
Output a prioritized list:
COMMAND AUDIT REPORT
Total commands: [count]
Healthy: [count]
Needs update: [count]
Stale (remove): [count]
Missing (create): [count]
UPDATES NEEDED:
1. [command] — [what to fix]
2. ...
COMMANDS TO ADD:
1. [name] — [what it would do]
2. ...
COMMANDS TO REMOVE:
1. [name] — [why it's stale]
2. ...
Step 5: Auto-Fix (if approved)
For each recommended change, ask for confirmation before:
- Updating command content
- Creating new command files
- Archiving stale commands (move to
commands/archive/)
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.
- yesterday First seen · 75 lines · 24 tokens per session scan A 59d72ed05897
ccc-improve-commands is a command published in the GitHub repository KevinZai/commander (6 stars, last pushed yesterday), licensed MIT. It adds 24 tokens to every session and 483 once invoked, about $0.0001 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 2026-09-03.
Other commands, from other repositories
whats-next
Show current project status and suggest next steps.
from-plan
Convert a Claude Code plan (or any spec file) into a task file and optionally hand it off to Cursor.
specmanager-build
Build one phase of a SpecManager feature's plan via the builder subagent. Stops at the phase boundary; never advances.
execute
Execute the next available tracked task with TDD, pre-commit validation, PR creation, AI code review, and issue tracker bridge sync.
phase
Orchestrate a full roadmap phase. Designs features, imports to tracker, creates issues, then executes.
roadmap
Generate or update a per-release roadmap from the PRD and analysis documents. Triages features, groups into phases, and produces a structured roadmap.