Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/KevinZai/commandernpx agentmods add commands/kevinzai/commander/ccc-improveWrote 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)<a href="https://agentmods.dev/commands/kevinzai/commander/ccc-improve"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc-improve/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/kevinzai/commander/ccc-improve"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc-improve.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 | $0.00047 | $0.02430 |
| Opus 5.5 | $0.00019 | $0.00972 |
| Sonnet 5.5 | $0.00009 | $0.00486 |
| Haiku 4.5 | $0.00005 | $0.00243 |
Grade A, and why
ccc-improve 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 5d 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 — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ccc-improve — continuous improvement pipeline
CC Commander · /ccc-improve · a scored queue of improvement proposals with approve, reject, and history views.
Parse the subcommand from $ARGUMENTS and run the matching section. With no subcommand, show the dashboard.
Routing
| Input | Section |
|---|---|
| (none) | Dashboard |
scan |
Scan |
scan --manual |
Manual proposal |
queue |
Queue |
evaluate <id> (or "evaluate " in chat) |
Evaluate |
approve <id> |
Approve |
reject <id> <reason> |
Reject |
auto |
Toggle auto-approval |
status |
Full statistics |
implemented |
Implementation history |
Data
Queue directory <queue>: $KZ_IMPROVE_QUEUE_DIR when set, otherwise ~/.claude/improvement-queue/.
| File | Contents |
|---|---|
prop-*.json |
one proposal each; status is pending, approved, rejected or implemented |
scan-log.json |
scan history: timestamp, findings, new proposals |
approved.json |
implementation queue, sorted by priority (impact - effort) |
implemented.json |
shipped proposals |
config.json |
{ "auto_approve": false } |
If <queue> does not exist, say no scan has run yet and suggest /ccc-improve scan.
Dashboard (default)
Read every prop-*.json, count by status, and read the last entry of scan-log.json:
CONTINUOUS IMPROVEMENT PIPELINE
===============================
Pending: <n> proposals awaiting review
Approved: <n> queued for implementation
Rejected: <n> declined
Implemented: <n> shipped
Last Scan: <timestamp> (<n> findings)
Auto-Approve: <ON/OFF> (documentation + impact <= 2)
Then ask what to do next with AskUserQuestion (plain-text question where unavailable): 🟢 Review the queue · Run a scan now · Full statistics.
Scan
-
Run the scanner, first path that exists:
node ~/.claude/hooks/daily-improvement-scan.js # repo checkout fallback: node hooks/daily-improvement-scan.js
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.
- 5d ago Changed · -72 lines · +25 tokens per session 036321536a67
- 1mo ago First seen · 332 lines · 22 tokens per session scan A 27154929549c
ccc-improve is a command published in the GitHub repository KevinZai/commander (6 stars, last pushed today), licensed MIT. It adds 47 tokens to every session and 2,430 once invoked, about $0.0002 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 2026-09-03.
Other commands, from other repositories
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.
dashboard
Compact visual progress dashboard with progress bar, task table, dependency graph, and active/blocked/next status.
sync
Reconcile coco tracker state with the configured issue tracker. Syncs task statuses and reports mismatches.
standup
Show a daily standup summary with completed, in-progress, and blocked tasks across all active epics.
status
Show current execution status with progress, dependencies, file ownership, and parallelization opportunities.