verify

verify is a skill for Claude Code, Codex from qinghaoliqaq/AutoCoder. It costs 42 tokens per session (597 once invoked), scanned A, original, Apache-2.0.

A skill for checking recent code changes by building the project, running tests, and exercising the affected features. It can also check relevant error cases and user-interface behavior.

In plain words
What is it for?
Use it when someone asks to verify a feature or change, or requests an end-to-end check after implementation.
Why use it?
It replaces assumptions that a change works with evidence from the project’s build, tests, and actual execution.

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/qinghaoliqaq/autocoder/verify
Any agent
npx skills add qinghaoliqaq/AutoCoder --skill verify
Clone the repo
git clone --depth 1 https://github.com/qinghaoliqaq/AutoCoder

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 verify

README.md
[![agentmods](https://agentmods.dev/badge/skills/qinghaoliqaq/autocoder/verify.svg)](https://agentmods.dev/skills/qinghaoliqaq/autocoder/verify)
Your own site
<a href="https://agentmods.dev/skills/qinghaoliqaq/autocoder/verify"><img src="https://agentmods.dev/badge/skills/qinghaoliqaq/autocoder/verify.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 597 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 $0.00042 $0.00597
Opus 5 $0.00021 $0.00298
Sonnet 5 $0.00008 $0.00119
Haiku 4.5 $0.00004 $0.00060

Measured 4d ago against content hash abfe5959ca03, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

verify 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 4d 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.

- Use curl/fetch to test affected API endpoints
src-tauri/src/bundled_skills/verify/SKILL.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verify — End-to-End Verification of Code Changes

Verify that recent code changes actually work by running the application and testing the affected functionality.

Approach

Step 1: Identify What Changed

  • Read recent git diff or changed files to understand the scope of changes
  • Identify which features, endpoints, or UI components were modified
  • Determine what needs to be tested

Step 2: Build & Compile

  • Run the project's build command (cargo build, npm run build, etc.)
  • Fix any compilation or type errors
  • Ensure the build completes cleanly with no warnings related to changes

Step 3: Run Existing Tests

  • Execute the project's test suite (cargo test, npm test, etc.)
  • If specific test files exist for changed modules, run those first
  • Report any test failures — do NOT skip or ignore them

Step 4: Manual Verification

For backend changes:

  • Start the server if applicable
  • Use curl/fetch to test affected API endpoints
  • Verify request/response shapes match expectations
  • Test error cases (invalid input, auth failures, not found)

For frontend changes:

  • Check that the dev server starts without errors
  • Verify the changed UI renders correctly
  • Test interactive elements (forms, buttons, navigation)
  • Check responsive behavior if layout was changed

For library/utility changes:

  • Write a small test script exercising the changed functions
  • Verify edge cases mentioned in the change description

Step 5: Report

Provide a clear verification report:

VERIFICATION REPORT
==================
Build:     PASS/FAIL (details if fail)
Tests:     PASS/FAIL (X passed, Y failed — list failures)
Manual:    PASS/FAIL (what was tested and results)
Overall:   PASS/FAIL

If any step fails:

  1. Diagnose the root cause
  2. Fix the issue if it's clearly related to the recent changes
  3. Re-run verification after the fix
  4. Report what was fixed

Important Rules

  • Do NOT claim "all tests pass" without actually running them
  • Do NOT skip verification steps — if you can't run something, say so explicitly
  • Do NOT fix unrelated issues during verification — only fix what the changes broke
  • Report outcomes faithfully — failures are valuable information
  • If the project has no test infrastructure, note this and focus on build + manual testing

Read the full file on GitHub · 85 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. 4d ago First seen · 85 lines · 42 tokens per session scan A abfe5959ca03

Subscribe to this mod's changes

verify is a skill published in the GitHub repository qinghaoliqaq/AutoCoder (11 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 42 tokens to every session and 597 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

multi-agent

Run work across more than one agent — choose between the task subagent, the delegate tool, and a second agentica CLI in tmux driven by peer messages (listagents / sendmessage). Use when a job wants parallel workers, its own terminal, coordination between sessions, or you are choosing among task, delegate, and a second…

shibing624/agentica · 72 tokens

web-research

Use this skill for requests related to web research; it provides a structured approach to conducting comprehensive web research.

shibing624/agentica · 24 tokens

python-lib-analyzer

Analyze any Python library structure, explore modules, classes, and functions with signatures and documentation.

shibing624/agentica · 23 tokens

agentica

How to answer questions about the agentica product you are running inside — CLI flags, config.yaml profiles, API keys, models, sessions, resume, workspace, AGENTS.md standing rules, skills, logs, upgrade, and selfmanage. Use when asked how agentica works, how to configure or upgrade it, where state lives on disk…

shibing624/agentica · 89 tokens

svg-chart

Render data into a standalone SVG chart file — bar, line, or pie. Use when the user provides numbers (inline, JSON, or CSV) and asks for a chart, graph, plot, trend, comparison, breakdown, or any visual summary of the data. Produces a self-contained .svg viewable in any browser; no external libraries required.

NUGURI-7/CoCoWork · 75 tokens

evidence-calibration-review

Use when you want a per-claim evidence-tier audit on a text artifact before it ships — assign T1-T6 tiers to every load-bearing claim, surface calibration mismatches (high confidence on weak evidence, or honesty-theater under-claiming), and flag P11 (citation-as-decoration), P17 (pile-of-anecdotes-as-evidence), P54…

Avyayalaya/agent-council · 129 tokens