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 skills/kevinzai/commander/ccc-loopnpx skills add KevinZai/commander --skill ccc-loopgit clone --depth 1 https://github.com/KevinZai/commanderWhat 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 | $0.00043 | $0.02743 |
| Opus 5 | $0.00022 | $0.01372 |
| Sonnet 5 | $0.00009 | $0.00549 |
| Haiku 4.5 | $0.00004 | $0.00274 |
Grade A, and why
ccc-loop 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 2d 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
$ccc-loop — Loop Integration Guide
Claude Code has four loop primitives, not one. This skill is the entry point for all of them — pick the right primitive before you reach for /loop by habit.
The 4 loop types
| Type | Trigger | Stop criteria | CC Commander primitive | Best for |
|---|---|---|---|---|
| Turn-based | A user prompt | Claude judges "done" itself | Just run the skill directly; encode your manual verification steps as a SKILL.md so Claude can self-check |
Short one-off tasks |
| Goal-based | A manual prompt, real-time | Goal achieved OR max turns reached — an evaluator model checks your condition each time Claude tries to stop | /goal |
Tasks with a verifiable exit criterion (test count, score threshold, build passing) |
| Time-based | An interval | You cancel it, or the work completes (PR merged, queue empty) | /loop (local) + /schedule (cloud) |
Recurring work, polling external systems |
| Proactive | An event or schedule, no human in real time | Each task exits on its own goal; the routine runs until you turn it off | /schedule (heartbeat) + /goal (define done) + dynamic Workflow (orchestrate) + auto mode (no confirmation stops) |
Recurring streams of well-defined work — bug triage, migrations, dependency upgrades |
Deterministic, quantitative checks beat vague ones for every type above — "tests pass" and "score ≥ 90" are checkable; "looks good" is not.
Should this be a loop? (gate before you build one)
All four must be true, or the loop costs more than it returns:
- Recurs at least weekly — a one-time job is better served by one good prompt.
- Verification is automated — a test suite, type checker, linter, or build that can fail the work without a human in the room. No automated check means you're back to reading every diff — the exact job the loop was supposed to remove.
- Your token budget absorbs the waste — loops re-read context, retry, explore. That burns tokens whether the run ships anything or not.
- The agent has real tools — logs, a reproduction environment, the ability to run what it writes and see what breaks. Without that, the loop iterates blind.
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.
- 2d ago First seen · 165 lines · 43 tokens per session scan A 1214fc3459fd
ccc-loop is a skill published in the GitHub repository KevinZai/commander (6 stars, last pushed 2d ago), licensed MIT. It adds 43 tokens to every session and 2,743 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 2026-08-31.
Other skills, from other repositories
agile-product-owner
../../../product-team/agile-product-owner/skills/agile-product-owner/SKILL.md.
rulesync
Generates and syncs AI rule configuration files (.cursorrules, CLAUDE.md, copilot-instructions.md) across 20+ coding tools from a single source. Use when syncing AI rules, running rulesync commands, importing or generating rule files, or managing shared AI coding configurations.
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
backend-builder
Используй только внутри активного Codex Project Autopilot-проекта по утверждённому плану; не включай для обычных backend-задач вне автопилота.
loongsuite-pilot-insight
基于 LoongSuite Pilot / AI Coding Agent 日志生成事件洞察、组织洞察、数据质量、研发效能和 AI Native 使用类 SLS 报表时使用；包含 AI Coding 事件表语义，以及团队报表可选的部门维表、deptuser 组织关系、指标口径和公共 CTE，通常与 sls-dashboard-builder 一起使用。.