ccc-e2e

An end-to-end pre-release assessment that runs quality checks, unit tests using test-driven development, and end-to-end tests in three isolated workspaces. Test-driven development means writing tests as part of guiding the implementation; end-to-end tests check complete user flows.

In plain words
What is it for?
Use it to run parallel pre-release checks, record assessment phases, report critical findings, and create follow-up fix tasks.
Why use it?
It checks the main parts of a change before release and combines the results into one pass-or-fail verdict.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/kevinzai/commander/ccc-e2e
Any agent
npx skills add KevinZai/commander --skill ccc-e2e
Clone the repo
git clone --depth 1 https://github.com/KevinZai/commander

Made for: Claude Code, Codex.

Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,568 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 2d ago against content hash 95800951f6de, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

commander/cowork-plugin-codex/skills/ccc-e2e/SKILL.md · 249 lines

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>"

After the verdict is rendered, spawn ONE mcp__ccd_session__spawn_task chip per Critical finding:

  • title: imperative fix phrase under 60 chars
  • prompt: 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 branch
  • git rev-list --count main..HEAD 2>/dev/null → commits ahead
  • git diff --shortstat main..HEAD 2>/dev/null → diff size
  • test -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."

Read the full file on GitHub · 249 lines

Changes

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.

  1. 2d ago First seen · 249 lines · 47 tokens per session scan A 95800951f6de

Subscribe to this mod's changes

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.

Related

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.

rtk-ai/rtk · 45 tokens

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.

QwenLM/qwen-code · 66 tokens

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.

rtk-ai/rtk · 61 tokens

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.

QwenLM/qwen-code · 48 tokens

vscode-visual-regression

Write Storybook stories and visual regression tests for the Kilo VS Code extension webview UI.

Kilo-Org/kilocode · 25 tokens

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…

entireio/cli · 89 tokens