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-compound)<a href="https://agentmods.dev/commands/kevinzai/commander/ccc-compound"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc-compound/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-compound"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc-compound.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 | $0.00046 | $0.01105 |
| Opus 5.5 | $0.00018 | $0.00442 |
| Sonnet 5.5 | $0.00009 | $0.00221 |
| Haiku 4.5 | $0.00005 | $0.00111 |
Grade A, and why
ccc-compound 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ccc-compound — persist what this task taught
CC Commander · /ccc-compound · post-task learning capture so the next task starts cheaper. Pattern credit: Compound Engineering.
Arguments
$ARGUMENTS:
- empty — capture learnings from the current session (default flow below)
review— show accumulated lessons; change nothingprune— propose outdated lessons for removal; delete only after confirmation
If review
-
Read
tasks/lessons.mdand list~/.claude/learned-skills/(either may be absent; say so). -
Print:
COMPOUND REVIEW Lessons: <n> entries across <m> dates Learned skills: <k> files <lessons grouped by date, most recent first> -
Stop. Do not extract or write anything.
If prune
- Read
tasks/lessons.md, the projectCLAUDE.mdand the files each lesson names. - For each entry, decide whether it still applies to the current code. List the stale ones with a one-line reason each.
- Ask with AskUserQuestion (Codex: a plain-text question):
- 🟢 Remove the listed entries — edits
tasks/lessons.md - Pick entries one by one — confirm each before removing
- Keep everything — no change
- 🟢 Remove the listed entries — edits
- After editing, run
git diff --stat -- tasks/lessons.mdand report the removed line count. Stop.
Default: capture learnings
-
Review what just happened. Run in parallel:
git log --oneline -10 git diff --stat HEAD~3If
HEAD~3does not exist (new repo), usegit diff --statagainst the first commit or the working tree. Then scan the conversation for decisions made, corrections received and patterns discovered. -
Extract learnings into three groups; skip any group with nothing meaningful:
- Patterns: code patterns that worked (architecture, data flow, API design), tool or library usage worth repeating, efficient workflow sequences.
- Corrections: what went wrong and its root cause, the fix, and how to prevent the class of error.
- Decisions: what was decided and why, alternatives rejected, constraints that drove it.
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 · -13 lines · +27 tokens per session f1887ff05d2e
- 1mo ago First seen · 124 lines · 19 tokens per session scan A 2463ed426d82
ccc-compound is a command published in the GitHub repository KevinZai/commander (6 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 1,105 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
status
Show current execution status with progress, dependencies, file ownership, and parallelization opportunities.
andrew-skills
Invoke Andrew Ng — Applied AI & Learning. Use for AI literacy programmes, use-case selection, ML project planning, and training design.
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.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.