code-acceptance

code-acceptance is a skill for Claude Code, Codex from leyuan0602-glitch/cc-claude-codex. It costs 68 tokens per session (2,505 once invoked), scanned A, original, MIT.

A test-based acceptance check for completed code changes. It runs unit, end-to-end, and integration tests and judges whether the required outcomes work, without reviewing the implementation style.

In plain words
What is it for?
Verifying requirements before committing or merging code, including scenarios described in a project status file or supplied directly.
Why use it?
It provides an evidence-based pass or fail decision instead of relying on an agent's claim that the work is complete. Only actual test results determine the result.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code; mentions Codex.

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/leyuan0602-glitch/cc-claude-codex/code-acceptance
Any agent
npx skills add leyuan0602-glitch/cc-claude-codex --skill code-acceptance
Clone the repo
git clone --depth 1 https://github.com/leyuan0602-glitch/cc-claude-codex

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for code-acceptance

README.md
[![agentmods](https://agentmods.dev/badge/skills/leyuan0602-glitch/cc-claude-codex/code-acceptance.svg)](https://agentmods.dev/skills/leyuan0602-glitch/cc-claude-codex/code-acceptance)
Your own site
<a href="https://agentmods.dev/skills/leyuan0602-glitch/cc-claude-codex/code-acceptance"><img src="https://agentmods.dev/badge/skills/leyuan0602-glitch/cc-claude-codex/code-acceptance.svg" alt="Measured on agentmods" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,505 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 5.1 $0.00068 $0.02505
Opus 5 $0.00034 $0.01252
Sonnet 5 $0.00014 $0.00501
Haiku 4.5 $0.00007 $0.00250

Measured 5d ago against content hash 7083dc71e253, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

code-acceptance scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| Dev Server | `npm run dev` / `python manage.py runserver` / etc. | `curl -sf http://localhost:PORT/` poll | `kill $PID` / `taskkill /F /PID` |
code-acceptance/SKILL.md · 263 lines

How it starts

The opening of the file, as written. The whole thing — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Acceptance: Test-Based Verification

You are an independent code acceptance verifier. Your job is to verify that code changes produce the expected outcomes through automated tests. You do NOT review code implementation — only test results determine PASS or FAIL.

Core Principles

  1. Zero trust — Never trust the executor's claims (Codex, developer, or any agent). All judgments come from running actual tests.
  2. Tests are the only evidence — PASS/FAIL is determined solely by whether tests pass. No code review, no style opinions, no implementation critique.
  3. Outcome over implementation — You don't care HOW the code works, only THAT it works as specified by the requirements.

Input Collection

Mode A: cc-claude-codex Integration

When called from cc-claude-codex Phase 3:

  • Requirements: Read .cc-claude-codex/status.md → extract ### Requirement: blocks and #### Scenario: (Given/When/Then)
  • Changes: git diff HEAD~1 --stat (for changed files overview only)
  • Reference data: Codex's returned progress and final output — marked [REF], used for cross-checking only, never as evidence

Mode B: Standalone

When invoked directly:

  • Requirements: From conversation context, or ask the user
  • Changes: git diff HEAD~1 --stat (default), or user-specified diff range
  • If no clear requirements provided: run existing test suite only

Step 0: Build Context

  1. Run git diff HEAD~1 --stat → list changed files
  2. Read requirements source (status.md or conversation)
  3. Build scenario checklist: list every Given/When/Then scenario to verify

Step 0.5: Infrastructure Detection

Scan the project to determine what infrastructure is needed for verification:

  1. Detect requirements — check these sources:
    • package.jsondev, start, serve scripts → NEEDS_DEV_SERVER
    • docker-compose*.yml exists → NEEDS_DOCKER
    • status.md### Infrastructure section → Remote Target / Health Endpoint populated → NEEDS_REMOTE_VERIFY / NEEDS_HEALTH_POLL
  2. Output detection checklist — record which flags are active before proceeding
  3. If no infrastructure needed — skip directly to Test-Based Verification

Read the full file on GitHub · 263 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. 5d ago First seen · 263 lines · 68 tokens per session scan A 7083dc71e253

Subscribe to this mod's changes

code-acceptance is a skill published in the GitHub repository leyuan0602-glitch/cc-claude-codex (9 stars, last pushed 6mo ago), licensed MIT. It adds 68 tokens to every session and 2,505 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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

testing

Testing workflow and quality standards for writing and running tests. Use when: (1) Writing new tests, (2) Adding a new feature that needs tests, (3) Modifying logic that has existing tests, (4) Before claiming a task is complete.

iOfficeAI/AionUi · 55 tokens

testing-patterns

Testing patterns and principles. Unit, integration, mocking strategies.

vudovn/ag-kit · 16 tokens

testing

Writing or debugging tests, choosing unit vs integration style, Postgres/ClickHouse tests, regenerating ClickHouse test schema, or exporting test helpers from packages without pulling test code into production bundles.

latitude-dev/latitude-llm · 41 tokens

detect-flaky-tests

Detects flaky Go tests by analyzing GitHub Actions workflow runs across the last 7 days and all PRs — covering both the run-tests job (unit/integration) and the e2e-test job (gVisor and microVM lanes). For each newly-detected flaky test or infra issue, opens a GitHub issue with full evidence and a draft fix PR. Does…

agent-substrate/substrate · 102 tokens

test-pyramid

Analyze the repo's unit and E2E tests and propose rebalancing toward a test pyramid — which E2E tests (or assertions inside them) can be covered by unit tests, which unit-level gaps genuinely need E2E coverage, and where coverage is duplicated. Use when the user asks about test pyramid, test rebalancing, "should this…

kubernetes-sigs/agent-sandbox · 104 tokens

designing-tests

Designs and implements testing strategies for any codebase. Use when adding tests, improving coverage, setting up testing infrastructure, debugging test failures, or when asked about unit tests, integration tests, or E2E testing.

CloudAI-X/claude-workflow-v2 · 48 tokens