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-e2enpx skills add KevinZai/commander --skill ccc-e2egit 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 | $0.00047 | $0.02568 |
| Opus 5 | $0.00023 | $0.01284 |
| Sonnet 5 | $0.00009 | $0.00514 |
| Haiku 4.5 | $0.00005 | $0.00257 |
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 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 — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
$ccc-e2e — End-to-End Pre-Release Assessment
CC Commander · $ccc-e2e · Full-surface confidence before you ship
Composes $ccc-fleet + $ccc-testing to run a full pre-release assessment in parallel across 3 isolated worktrees. One command. Three workers. One verdict.
Session markers
Call mcp__ccd_session__mark_chapter at these phase transitions:
| Trigger | title | summary |
|---|---|---|
| After user confirms scope, before fan-out | "E2E assessment: <branch>" |
"3-worker fan-out starting on <branch>" |
| When all workers have reported back | "E2E workers complete" |
"QA: <status> / Unit-TDD: <status> / E2E: <status>" |
| After verdict is written | "E2E verdict: <PASS/FAIL>" |
"<N> Critical, <N> High — verdict: <PASS/FAIL>" |
Sidebar chips (spawn_task)
After the verdict is rendered, spawn ONE mcp__ccd_session__spawn_task chip per Critical finding:
title: imperative fix phrase under 60 charsprompt: self-contained — include the worker that reported it, file:line if available, issue summary, and fix direction. The spawned session has no memory of this conversation.tldr: 1-2 sentences plain English.
Only Critical findings get chips. High/Medium/Low go into the verdict artifact as TodoWrite items.
Response shape (EVERY time)
1. Brand header
**CC Commander** · $ccc-e2e · Full-surface pre-release confidence
2. Context strip
Four parallel reads (silent on failure):
git rev-parse --abbrev-ref HEAD→ current branchgit rev-list --count main..HEAD 2>/dev/null→ commits aheadgit diff --shortstat main..HEAD 2>/dev/null→ diff sizetest -f package.json && node -p "require('./package.json').version"→ version
Render one line:
🧭 Branch:
<branch>· commits ahead · files changed · version:<ver>
3. Scope picker — AskUserQuestion
question: "What scope should I assess?"
header: "CC Commander E2E"
multiSelect: false
options:
- label: "🔬 Full assessment (QA + Unit-TDD + E2E)"
description: "3 parallel workers. ~15-30 min. Use before tagging a release."
preview: "Most thorough. 3 worktrees, 3 agents, severity-ranked verdict."
- label: "🧪 QA + Unit-TDD only (no E2E)"
description: "2 workers. ~8-15 min. Use for non-UI changes."
preview: "Skips Playwright. Good for API/library changes."
- label: "🎭 E2E only (Playwright)"
description: "1 worker. ~5-10 min. Use when fixing a specific UI regression."
preview: "Runs $ccc-testing e2e-testing + visual-regression only."
- label: "🏃 Quick QA pass only"
description: "1 worker. ~3-5 min. Use for sanity check, not release gate."
preview: "Runs $ccc-testing qa-only. Finds but does not fix."
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 · 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 3d ago), licensed MIT. It adds 47 tokens to every session and 2,568 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
tdd-rust
TDD workflow for RTK filter development. Red-Green-Refactor with Rust idioms. Real fixtures, token savings assertions, snapshot tests with insta. Auto-triggers on new filter implementation.
terminal-capture
Automates terminal UI screenshot testing for CLI commands. Applies when reviewing PRs that affect CLI output, testing slash commands (/about, /context, /auth, /export), generating visual documentation, or when 'terminal screenshot', 'CLI test', 'visual test', or 'terminal-capture' is mentioned.
rtk-tdd
Enforces TDD (Red-Green-Refactor) for Rust development. Auto-triggers on implementation, testing, refactoring, and bug fixing tasks. Provides Rust-idiomatic testing patterns with anyhow/thiserror, cfg(test), and Arrange-Act-Assert workflow.
feat-dev
End-to-end workflow for implementing a non-trivial qwen-code feature. Covers requirements investigation, design, E2E test planning, baseline dry-run, implementation, verification, self-audit, code review, and iteration.
vscode-visual-regression
Write Storybook stories and visual regression tests for the Kilo VS Code extension webview UI.
agent-integration
Run all three agent integration phases sequentially: research, write-tests, and implement using E2E-first TDD (unit tests written last). For individual phases, use /agent-integration:research, /agent-integration:write-tests, or /agent-integration:implement. Use when the user says "integrate agent", "add agent…