A read-only verification skill that runs a requested check and combines the results into severity-labelled findings.

Use it for unit, integration, or end-to-end tests, security scans, performance benchmarks, data-quality checks, or model evaluations.

It shows the current measurable state without making fixes, so problems can be handed to a separate repair step.

aid-test — Skill for Claude Code by AndreVianna/aid-methodology

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.

Any agent

npx skills add AndreVianna/aid-methodology --skill aid-test

Clone the repo

git clone --depth 1 https://github.com/AndreVianna/aid-methodology

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/andrevianna/aid-methodology/aid-test/github.svg)](https://agentmods.dev/skills/andrevianna/aid-methodology/aid-test)

Your own site

<a href="https://agentmods.dev/skills/andrevianna/aid-methodology/aid-test"><img src="https://agentmods.dev/badge/skills/andrevianna/aid-methodology/aid-test/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/andrevianna/aid-methodology/aid-test"><img src="https://agentmods.dev/badge/skills/andrevianna/aid-methodology/aid-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 111 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,570 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00111	$0.01570
Opus 5.5	$0.00044	$0.00628
Sonnet 5.5	$0.00022	$0.00314
Haiku 4.5	$0.00011	$0.00157

Measured 26d ago against content hash 753673b244ea, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

aid-test 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 26d 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.

.agents/skills/aid-test/SKILL.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test (run + consolidate, resolve nothing)

/aid-test runs the requested verification and consolidates the results -- it does not author tests (that is /aid-create-test, a keep-cycle create-family skill). It is review-shaped: run-a-tool is the evidence-gathering step, and consolidating results into severity-tagged findings that hand off to /aid-fix is exactly the /aid-review shape -- so this reuses aid-review's machinery (work folder, 7-column ledger, clean-context verify, present, printed-suggestion handoff). The three test-* kind-siblings (/aid-test-security, /aid-test-performance, /aid-test-data-quality) delegate here.

Read-only on the source; never fixes (findings -> /aid-fix).
Not a numbered pipeline phase; does not route to /aid-execute.

State machine: INTAKE -> RUN -> VERIFY (loop) -> PRESENT [human] -> HANDOFF? -> DONE. Print the [State: NAME] -- {purpose} entry line on each state.

State: INTAKE

Require a target. Empty argument -> ask one bootstrapping question ("What should I test or verify?") and wait.
Determine the verification kind from the request (or the kind a sibling bound): functional (unit/integration/e2e), security (SAST/DAST/fuzz/dependency-audit), performance (workload/threshold/environment), data-quality (schema/freshness/ completeness/uniqueness), or model-eval (run the eval harness, assert metric vs threshold). The framework is inferred from the KB (test-landscape.md).
Pick the path: Fast -- a clear target + kind ("run the security scan on the auth module", "benchmark the /orders endpoint vs the p99 SLO") -> run now. Guided -- vague -> scope target / kind / threshold first.
Classify complexity (model + effort): simple run -> aid-reviewer at sonnet / medium; deep security/perf analysis -> opus / high. Verifier tier >= producer.
Consult the Work Initiation Gate, then allocate the work folder + STATE. First run the gate (.aid/runtime/templates/work-initiation-gate.md): bash .aid/runtime/scripts/works/enumerate-works.sh (main tree + every git worktree). Empty -> allocate, no prompt. Works exist -> ask new-vs-continuation; on continuation route to the chosen work's resume door and STOP (allocate nothing); on new work: create and enter the worktree per the gate's § 3a step 2 (worktree-lifecycle.sh create <work-id> <name>, STOP on a non-zero exit or empty path, else enter the resolved path), then allocate (pipeline.path: lite, initiator: aid-test, lifecycle: Running, active_skill: aid-test; phase not driven).

Read the full file on GitHub · 127 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.

26d ago Changed 753673b244ea
2mo ago First seen · 127 lines · 111 tokens per session scan A f3b39a622a7b

Subscribe to this mod's changes

aid-test is a skill published in the GitHub repository AndreVianna/aid-methodology (6 stars, last pushed 11d ago), licensed MIT. It adds 111 tokens to every session and 1,570 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-03.

E2E testing Testing Unit testing

aid-test next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
aid-testAndreVianna/aid-methodology	Skill	6	11d ago	MIT	A	111	Claude Code
test-masterJeffallan/claude-skills	Skill	12k	8d ago	MIT	A	104	Claude Code
axiom-testingCharlesWiltgen/Axiom	Skill	1.3k	2d ago	MIT	A	38	Claude Code
test-generatorrshankras/claude-code-apple-skills	Skill	867	yesterday	MIT	A	33	Claude Code
testing-blocksadobe/skills	Skill	320	today	Apache-2.0	A	61	Claude Code
designing-testsCloudAI-X/claude-workflow-v2	Skill	1.4k	1mo ago	MIT	A	48	Claude Code
test-automation-expertcuriositech/some_claude_skills	Skill	263	2d ago	MIT	A	133	Claude Code