test-assess

A testing workflow for checking the AgentReady assessment tool against real GitHub repositories, which are hosted code projects.

In plain words
What is it for?
Use it to select suitable repositories, run the local assessor, review its results and output locations, and clean up temporary clones.
Why use it?
Testing on relevant repositories helps reveal whether a change to the assessor works across projects with different structures and maturity.

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/ambient-code/agentready/test-assess
Any agent
npx skills add ambient-code/agentready --skill test-assess
Clone the repo
git clone --depth 1 https://github.com/ambient-code/agentready

Made for: Claude Code, Codex.

Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 770 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 $0.00075 $0.00770
Opus 5 $0.00037 $0.00385
Sonnet 5 $0.00015 $0.00154
Haiku 4.5 $0.00007 $0.00077

Measured 2d ago against content hash a61600b8e53d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

test-assess 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.

.claude/skills/test-assess/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test agentready assess on real repositories

You are testing the agentready assessment tool against real GitHub repositories to validate that a change works correctly.

1. Determine what to test

The user will describe what assessor behavior they want to validate (e.g., "test Husky detection", "verify the new CI gates assessor"). If the description is unclear, ask a brief clarifying question.

2. Ensure the code under test is checked out

Check which branch is currently active. If the change being tested is on a different branch or PR, check it out first. If it is a PR, use gh pr checkout <number>.

3. Select repositories

Search GitHub for repositories that are relevant to the feature being tested. For example, if testing Husky hook detection, find repos that use Husky.

How many repos:

  • Small or targeted changes: at least 1 repo
  • Larger or riskier changes: 3 to 5 repos

Selection criteria (in priority order):

  1. Relevance: repos must exercise the specific behavior being tested. This is the most important criterion.
  2. Variety of maturity: when possible, mix large popular projects with smaller or newer ones. But never sacrifice relevance for variety.

Use gh search repos, gh api, or gh search code to find candidates. Briefly confirm your repo selections with the user before cloning.

4. Clone repos to a temp directory

Create a unique temp directory for this test run:

TESTDIR=$(mktemp -d /tmp/agentready-test-XXXXXX)

Shallow clone each repo into that directory:

git clone --depth 1 <repo-url> $TESTDIR/<repo-name>

5. Run assessments

Run each assessment using the local checkout, not the globally installed package:

yes | PYTHONPATH=src python -m agentready assess $TESTDIR/<repo-name>

The yes | prefix auto-confirms the large-repo prompt if it appears.

6. Report results

After each assessment completes, report to the user:

  • The repo name and the overall score/certification level
  • The specific finding(s) relevant to what is being tested, including status, score, and evidence
  • The exact paths to the JSON, HTML, and Markdown reports so the user can inspect them

Read the full file on GitHub · 99 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 · 99 lines · 75 tokens per session scan A a61600b8e53d

Subscribe to this mod's changes

test-assess is a skill published in the GitHub repository ambient-code/agentready (151 stars, last pushed 6d ago), licensed MIT. It adds 75 tokens to every session and 770 once invoked, about $0.0004 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 2026-08-30.

Related

Other skills, from other repositories

release-candidate-prep

Preflight and prepare an OpenAI Agents Python release candidate in a dedicated worktree from exact origin/main, gate readiness before branch creation, freeze the released API contract, create or replace the local release branch with one release commit, enforce final release review as a checker, and produce…

openai/openai-agents-python · 87 tokens

magpie-setup

Adopt and maintain the apache-magpie framework in a project repo via the snapshot-based adoption mechanism. The only framework skill committed in an adopter's repo; every other skill is a symlink the adopt sub-action wires up. Sub-actions: /magpie-setup - first-time adoption (default; main-checkout only) /magpie-setup…

apache/airflow · 243 tokens

stripe-best-practices

Guides Stripe integration decisions across API selection (Checkout Sessions vs PaymentIntents), Connect platform setup (Accounts v2, controller properties), billing/subscriptions, tax and registrations (Stripe Tax, automatictax, product tax codes), Treasury financial accounts, integration options (Checkout, Payment…

stripe/ai · 134 tokens

billing-stripe

Work with Stripe billing — subscriptions, plans/prices, the Customer Portal, credits, usage metering, invoices, and webhook events. Use when changing plans, handling a new Stripe webhook, debugging a payment/subscription flow, or touching credit balances and usage.

vstorm-co/full-stack-ai-agent-template · 56 tokens

refactor

Refactor code to improve structure and maintainability.

vstorm-co/pydantic-deepagents · 12 tokens

test-writer

Generate comprehensive test suites for existing code.

vstorm-co/pydantic-deepagents · 11 tokens