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/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-rules-distill)<a href="https://agentmods.dev/commands/kevinzai/commander/ccc-rules-distill"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc-rules-distill/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-rules-distill"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc-rules-distill.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 | $0.00038 | $0.00576 |
| Opus 5.5 | $0.00015 | $0.00230 |
| Sonnet 5.5 | $0.00008 | $0.00115 |
| Haiku 4.5 | $0.00004 | $0.00058 |
Grade B, and why
ccc-rules-distill scanned grade B with 1 finding 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.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
ls -d ~/.claude/skills/*/SKILL.md .claude/skills/*/SKILL.md 2>/dev/null How it starts
The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ccc-rules-distill — turn repeated skill guidance into rules
CC Commander · /ccc-rules-distill · a reviewed list of cross-cutting principles, promoted into rule files you approve.
What happens
-
Load the
rules-distillskill with the Skill tool and follow its workflow. It is an opt-in skill, absent by default. If it is not listed in this session, say so and continue with steps 2 to 6, which are the minimal version of the same workflow. -
Inventory the sources. List skill files and existing rules, and report which paths were found:
ls -d ~/.claude/skills/*/SKILL.md .claude/skills/*/SKILL.md 2>/dev/null ls ~/.claude/rules .claude/rules 2>/dev/nullIf no skills are found, say so and stop.
-
Read each skill and extract principles: imperative guidance that is not specific to that skill's domain (for example "validate input at boundaries", "verify before reporting done").
-
Keep a principle only when it appears in two or more skills. For each, record the skills that state it (
path:line) and whether an existing rule already covers it. Drop candidates an existing rule already states; link to that rule instead. -
Present the candidates as a table: principle, source skills, proposed rule file, new or amend. Then ask with AskUserQuestion (Codex: a plain-text question):
- 🟢 Write approved rules — add or amend only the rows the user keeps
- Show the evidence — print the quoted lines for each candidate first
- Save the report only — write nothing to the rules directory
- Cancel — nothing is written
-
For each approved row, write or amend one rule file per topic (short, one topic, no restating another rule). Then verify: read each file back, and run
git diff --statwhen the rules live in a git repository. Report the files changed.
Done when
Every proposed rule names at least two source skills, and every written rule file has been read back and listed in the report.
Guardrails
- Never edit a skill file during distillation; this command only writes rules.
- Never write a rule the user did not approve in the picker.
- Never duplicate a rule that already exists; amend or link instead.
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 · +32 lines · +24 tokens per session scan A → B e946464b4b43
- 1mo ago First seen · 12 lines · 14 tokens per session scan A 6ebde0e28057
ccc-rules-distill is a command published in the GitHub repository KevinZai/commander (6 stars, last pushed today), licensed MIT. It adds 38 tokens to every session and 576 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other commands, from other repositories
loop
Autonomous execution loop. Runs the TDD cycle repeatedly until all tasks in an epic are complete, with circuit breaker protection and PR workflow.
phase
Orchestrate a full roadmap phase. Designs features, imports to tracker, creates issues, then executes.
status
Show current execution status with progress, dependencies, file ownership, and parallelization opportunities.
justone-publish
Publish a completed JustOne build — create a public GitHub repo, push, and register on the gallery.
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.