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-initgit 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-init)<a href="https://agentmods.dev/commands/kevinzai/commander/ccc-init"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc-init.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 | $0.00032 | $0.00713 |
| Opus 5 | $0.00016 | $0.00357 |
| Sonnet 5 | $0.00006 | $0.00143 |
| Haiku 4.5 | $0.00003 | $0.00071 |
Grade A, and why
ccc-init 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.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ccc-init — Project Initialization + Refresh
One command for both new projects and existing stale CLAUDE.md refreshes. Replaces /ccc-refresh (kept as deprecated alias).
What this does
- Detects current project state:
- No CLAUDE.md → scaffold from
CLAUDE.md.template - CLAUDE.md older than 30 days OR template version mismatch → refresh proposal
- CLAUDE.md current → report healthy + offer optional sections
- No CLAUDE.md → scaffold from
- Creates
tasks/directory +tasks/lessons.mdif missing - Creates
.claude/settings.jsonscaffold if missing (project-scoped permissions) - Shows a merge plan with ADD / UPDATE / KEEP / CUSTOM classifications
- Applies only after explicit confirmation
- Updates version comment to:
<!-- CC Commander Template v4.0.0-beta.1 | Generated: YYYY-MM-DD -->
Scaffold paths (new project)
project-root/
├── CLAUDE.md # from CLAUDE.md.template
├── tasks/
│ ├── todo.md # stub
│ └── lessons.md # empty header
└── .claude/
└── settings.json # project-level scaffold
Refresh strategy (existing project)
Same H2-section merge behavior as legacy /ccc-refresh:
- MATCH — header exists in both, compare bodies
- MISSING — in template but not user's → recommend adding with
<!-- Added by CC Commander v4.0.0-beta.1 --> - CUSTOM — user has it, template doesn't → preserved untouched
- UPDATE — content drift → side-by-side proposal
Auto-prompt triggers
The session-start hook proactively nudges when:
- CLAUDE.md missing entirely
- Template version older than installed CC Commander
- File unmodified >30 days
- Key H2 sections missing (Workflow, Core Principles, Rules)
Override via CC_NUDGE_DISABLE=1.
Deprecated alias
/ccc-refresh is preserved as a deprecated alias — calling it emits a deprecation notice, then executes /ccc-init refresh behavior.
Example
User: /ccc-init
CC Commander:
# Project Initialization
## State detected
- CLAUDE.md: present, v2.1.0 → v4.0.0-beta.1 available
- tasks/lessons.md: missing
- .claude/settings.json: missing
- Last modified: 47 days ago
## Proposed actions
+ [SCAFFOLD] tasks/lessons.md
+ [SCAFFOLD] .claude/settings.json (project permissions scaffold)
~ [REFRESH] CLAUDE.md — 6 new H2 sections, 4 updated
= [KEEP] "My Custom Rules" section (untouched)
Apply? (yes / no / show-diff)
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 · 81 lines · 32 tokens per session scan A f85fb2d658ce
ccc-init is a command published in the GitHub repository KevinZai/commander (6 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 713 once invoked, about $0.0002 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.
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.
dashboard
Compact visual progress dashboard with progress bar, task table, dependency graph, and active/blocked/next status.