multica-review-test

multica-review-test is a skill for Claude Code, Codex from it235/multica-best-practices. It costs 57 tokens per session (452 once invoked), scanned A, original, MIT.

A review checklist for test cases, test reports, and coverage documents. It checks whether the tests cover the agreed requirements and whether their conclusions match the evidence.

In plain words
What is it for?
It is used to review test artifacts and return PASS or FAIL with required fixes. It covers normal, boundary, error, permission, and compatibility cases, plus links between acceptance criteria and executable tests.
Why use it?
It helps catch missing important paths, unsupported pass or fail claims, and mismatches between tests and the backend contract before the work is accepted.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It is used to review test artifacts and return PASS or FAIL with required fixes. It covers normal, boundary, error, permission, and compatibility cases, plus links between acceptance criteria and executable tests.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/it235/multica-best-practices/multica-review-test
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 it235/multica-best-practices --skill multica-review-test
Clone the repo
git clone --depth 1 https://github.com/it235/multica-best-practices

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 multica-review-test

README.md
[![agentmods](https://agentmods.dev/badge/skills/it235/multica-best-practices/multica-review-test/github.svg)](https://agentmods.dev/skills/it235/multica-best-practices/multica-review-test)
Your own site
<a href="https://agentmods.dev/skills/it235/multica-best-practices/multica-review-test"><img src="https://agentmods.dev/badge/skills/it235/multica-best-practices/multica-review-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.

agentmods 80×15 button for multica-review-test

Your own site · 80×15
<a href="https://agentmods.dev/skills/it235/multica-best-practices/multica-review-test"><img src="https://agentmods.dev/badge/skills/it235/multica-best-practices/multica-review-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 452 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00057 $0.00452
Opus 5 $0.00028 $0.00226
Sonnet 5 $0.00011 $0.00090
Haiku 4.5 $0.00006 $0.00045

Measured 3d ago against content hash 7cfce1d9306d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

multica-review-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 3d 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.

templates/en_US/skills/multica-review-test/SKILL.md · 39 lines

What it actually says

Test Artifact Professional Review (TestReviewer)

Structured professional review framework for test artifacts (functional/API cases, test report, coverage doc). Called by TestReviewer; reviews the links Tester returns via multica-test-orchestration (case set / report), plus acceptance + related implementation change links Leader passes.

When to use

  • TestReviewer receives a "review test artifact" dispatch from Leader (case review / report review both apply).
  • Entering a re-review round after test-artifact changes (check previous round's fix list item by item).

Review dimensions (conclusion per item)

  1. Coverage depth: normal / boundary / exception / permission / compatibility paths covered.
  2. Acceptance mapping: every AC- backed by an executable case.
  3. Coverage reasonableness: metrics truly reflect risk points, no hiding critical uncovered paths.
  4. Conclusion truth: pass/fail based on real execution evidence, defects reproducible.
  5. Contract consistency: case params, assertions aligned with BackendDev contract.

Output format

【Test Artifact Review】<test link>
Conclusion: PASS / FAIL
Blocking items (required on FAIL, each: rationale / involved point / fix direction):
- ...
Suggestions (non-blocking):
- ...
Previous fix-list check (re-review): resolved X / unresolved Y
Round: N / 3

Conclusion + fix list reported to Leader; don't modify cases or notify Tester yourself.

Boundaries

  • Review only test artifacts, not architecture, requirements, UI, frontend/backend implementation, or code unit tests.
  • Don't replace Leader's generic gate (multica-verification skill).
  • Implementation-layer quality goes to the matching dedicated Reviewer; you own test-artifact professionalism.
  • Still FAIL at round 3 → mark "escalate to human", hand to Leader, stop looping.
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. 3d ago Changed 7cfce1d9306d
  2. 10d ago First seen · 39 lines · 57 tokens per session scan A 56d757b44d3c

Subscribe to this mod's changes

multica-review-test is a skill published in the GitHub repository it235/multica-best-practices (108 stars, last pushed yesterday), licensed MIT. It adds 57 tokens to every session and 452 once invoked, about $0.0003 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