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-e2egit 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-e2e)<a href="https://agentmods.dev/skills/kevinzai/commander/ccc-e2e"><img src="https://agentmods.dev/badge/skills/kevinzai/commander/ccc-e2e/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-e2e"><img src="https://agentmods.dev/badge/skills/kevinzai/commander/ccc-e2e.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 226 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 4 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00070 | $0.02243 |
| Opus 5.5 | $0.00028 | $0.00897 |
| Sonnet 5.5 | $0.00014 | $0.00449 |
| Haiku 4.5 | $0.00007 | $0.00224 |
Grade A, and why
ccc-e2e 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
$ccc-e2e — Full-surface confidence before shipping
CC Commander · $ccc-e2e · parallel QA, unit and E2E workers, one honest verdict
Composes $ccc-fleet (parallel dispatch, worktree isolation) with $ccc-testing (testing lanes). Audit only: workers find and report, they do not fix.
When to use / when not to
- Use before tagging a major or minor release, after merging a feature that touches five or more files, after a cross-module refactor, or when the user feels coverage is thin but cannot say where.
- Quick bug-fix patch:
$ccc-review. Single-file change:$ccc-testing. Docs-only change: skip. Hotfix under time pressure:$ccc-shippre-flight. - Codex: ask pickers as plain-text questions and run each worker as
codex exec --json --sandbox workspace-writein its owngit worktree; the session tools below are skipped.
What happens
1. Context strip
Run in parallel, silent on failure:
git rev-parse --abbrev-ref HEAD
BASE=$(git symbolic-ref --short refs/remotes/origin/HEAD 2>/dev/null | sed 's#^origin/##'); BASE=${BASE:-main}
git rev-list --count "$BASE"..HEAD 2>/dev/null
git diff --shortstat "$BASE"..HEAD 2>/dev/null
git diff --name-only "$BASE"..HEAD 2>/dev/null
test -f package.json && node -p "require('./package.json').version"
Render one line: 🎯 Branch: <branch> · <N> commits ahead of <base> · <X> files changed · version: <ver>.
2. Scope
If $ARGUMENTS is status, jump to "Status" below. If it is full, qa-unit, e2e-only or quick (qa-only is an alias for quick), use it and skip the picker. Otherwise ask the scope picker (Decision points).
After scope is set, call mcp__ccd_session__mark_chapter with title "E2E assessment: <branch>" and summary "<N>-worker fan-out starting on <branch>".
3. Fan out workers
Dispatch with the Agent tool, following $ccc-fleet's Agent-tool rules. Send every worker call in one message so they start together. Every call uses:
subagent_type: "qa-engineer"(general-purposeif the plugin agent is not registered)model: "sonnet",effort: "medium",isolation: "worktree",run_in_background: true- a prompt that starts: "FIRST: run
git rev-parse --show-toplevel. It must be your assigned worktree, not the main checkout; abort and report if it is not. Audit only: do not fix, commit, push or merge."
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · -81 lines · +23 tokens per session 88e5ccc6f0bf
- 1mo ago First seen · 249 lines · 47 tokens per session scan A 95800951f6de
ccc-e2e is a skill published in the GitHub repository KevinZai/commander (6 stars, last pushed today), licensed MIT. It adds 70 tokens to every session and 2,243 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
tdd
Use before implementation when behavior can be verified by automated tests and regression coverage has clear value. For bugs with an unknown root cause, use systematic-debugging first, then return for red-green. Follow red-green-refactor—write a failing test first, add only enough code to pass it, then refactor. Do…
execute
Execute the next available tracked task with TDD, pre-commit validation, PR workflow, AI code review, and issue tracker bridge sync. Primary execution interface for multi-session feature work.
qa-test-planner
Generate comprehensive test plans, manual test cases, regression test suites, and bug reports for QA engineers. Includes Figma MCP integration for design validation.
tdd
Build this test-first, one behavior at a time: $ARGUMENTS.
memstack-development-test-writer
Use this skill when the user says 'write tests', 'add tests', 'test coverage', 'unit tests', 'integration tests', 'component tests', 'mocking', 'edge cases', or needs to generate tests with proper mocking and edge case coverage. Do NOT use for refactoring plans or database migrations.
memstack-development-webapp-testing
Use when the user says 'write browser tests', 'test this page', 'playwright test', 'e2e test', 'end to end test', 'browser test', 'test the UI', or needs Playwright-based browser testing for a web application. Do NOT use for unit tests, API tests, or non-browser testing.