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 skills add KevinZai/commander --skill ccc-tasksgit 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/skills/kevinzai/commander/ccc-tasks)<a href="https://agentmods.dev/skills/kevinzai/commander/ccc-tasks"><img src="https://agentmods.dev/badge/skills/kevinzai/commander/ccc-tasks/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/skills/kevinzai/commander/ccc-tasks"><img src="https://agentmods.dev/badge/skills/kevinzai/commander/ccc-tasks.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 | $0.00062 | $0.01249 |
| Opus 5.5 | $0.00025 | $0.00500 |
| Sonnet 5.5 | $0.00012 | $0.00250 |
| Haiku 4.5 | $0.00006 | $0.00125 |
Grade A, and why
ccc-tasks 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 11d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
$ccc-tasks — Markdown task tracking
CC Commander · $ccc-tasks · one file, markdown checkboxes, a git-visible audit trail
When to use / when not to
- Use for personal projects that do not need a tracker, side-session tracking while a larger ticket is in flight, brainstorm capture before picking one or two to execute, and a reviewable audit trail in git.
- Team coordination with two or more people: use
$ccc-linear. - Long-term milestones: use a tracker project.
- Sub-tasks of a complex feature: use the feature's spec doc and the session's task tool.
- In Codex, ask each picker below as a plain-text question with the same options.
File format
tasks/todo.md in the project root:
# Todo
## Active
- [~] P0 · Ship the release candidate
- note: smoke test passes locally, CI pending
- [ ] P1 · Add retry to the webhook handler
- [x] P0 · Fix silent MCP startup failure ✅ 2026-04-23
## Blocked
- [!] P1 · Launch post — waiting on the demo recording
## Someday
- [ ] Editor companion extension
Priorities: P0 this week · P1 this month · P2 this quarter · P3 someday.
Status: [ ] todo · [~] in progress · [x] done (with date) · [!] blocked (with a blocker note).
What happens
1. Read the file
test -f tasks/todo.md && cat tasks/todo.md || echo "no tasks/todo.md"
Missing: ask with AskUserQuestion "🟢 Create tasks/todo.md with the empty sections" or "Cancel". Create it with Write only on yes. This is the only time the skill writes the whole file.
2. Route by argument
$ARGUMENTS |
Step |
|---|---|
empty, list |
Show Active and Blocked, then step 3 |
pick |
Step 3 |
add |
Step 4 |
done |
Step 5 |
prune |
Step 6 |
3. Pick one to work on
Ask with AskUserQuestion: up to 4 open items, P0 first, the recommended one first and marked 🟢, each description naming its priority and section. On pick, move it under Active if it is not there, mark it [~], and state the scope in one sentence.
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.
- 11d ago Changed · +48 lines · +23 tokens per session 037e1a456501
- 1mo ago First seen · 78 lines · 39 tokens per session scan A 4864b5adfa8e
ccc-tasks is a skill published in the GitHub repository KevinZai/commander (6 stars, last pushed yesterday), licensed MIT. It adds 62 tokens to every session and 1,249 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 skills, from other repositories
hotfix
Single-issue workflow for quick fixes and small changes that don't need full epic tracking. Creates a branch, implements the fix, commits with issue tracking, and closes.
github-workflow
GitHub best practices for pull requests, code reviews, issues, Actions workflows, and repository management.
lerna
Best practices for Lerna monorepo management, versioning, and publishing.
apex-status
CTO-level project status from git and codebase state. Use when asked "where are we", "project status", "what's done", or at the start of a work session.
github-activity
Report what happened across GitHub repositories over a time window, read only. Invoke when the user asks what merged, which issues were opened or closed, or what moved between milestones since a date or since the last report, across one or more repositories.
implement-issue
Turn one labelled GitHub issue into one reviewed pull request, or stop with a stated reason. Use for every factory run; the message is a link to the issue.