agentmods.dev

test-analyze

test-analyze is a skill for Claude Code, Codex from cohemm/prism. It costs 96 tokens per session (1,894 once invoked), scanned A, original, MIT.

A live test runner for the prism:analyze skill, which examines real codebases and produces analysis findings. It checks both the workflow and the evidence behind those findings.

In plain words
What is it for?
Use it to run end-to-end tests of prism:analyze, check that JSON output from one phase is read by the next, inspect real verification scores, and confirm that findings without code evidence score low.
Why use it?
It catches broken handoffs between analysis stages and helps prevent unsupported findings from receiving high verification scores.

Skill for Claude CodeCodex

Part of the prism plugin — 6 skills, 5 commands, 2 agents, 2 hooks, 1 MCP server shipped together

not rated 5 3mo ago A scan 96 tokens original MIT
View the source file cohemm/prism
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/cohemm/prism/test-analyze
Any agent
npx skills add cohemm/prism --skill test-analyze
Clone the repo
git clone --depth 1 https://github.com/cohemm/prism

Made for: Claude Code, Codex.

Or install prism, the plugin that ships this one along with the rest of its 6 skills, 5 commands, 2 agents, 2 hooks, 1 MCP server.

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 test-analyze

README.md
[![agentmods](https://agentmods.dev/badge/skills/cohemm/prism/test-analyze.svg)](https://agentmods.dev/skills/cohemm/prism/test-analyze)
Your own site
<a href="https://agentmods.dev/skills/cohemm/prism/test-analyze"><img src="https://agentmods.dev/badge/skills/cohemm/prism/test-analyze.svg" alt="Measured on agentmods" height="20"></a>
Per session 96 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,894 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 $0.00096 $0.01894
Opus 5 $0.00048 $0.00947
Sonnet 5 $0.00019 $0.00379
Haiku 4.5 $0.00010 $0.00189

Measured 4d ago against content hash b25c390852fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

test-analyze 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 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.

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.

skills/test-analyze/SKILL.md · 194 lines

How it starts

The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.

test-analyze: Live Test Runner for prism:analyze

Run live end-to-end tests of the prism:analyze skill with real code analysis, real MCP verification, and automated grading.

All test fixtures for this skill must remain self-contained under skills/test-analyze/:

  • skills/test-analyze/evals/evals.json
  • skills/test-analyze/references/
  • skills/test-analyze/test-results/ when generated

Treat paths in evals/evals.json as relative to this skill directory unless they are explicitly absolute target-codebase inputs.

What This Skill Tests

Three categories of assertions, each verified against real execution artifacts:

  1. Workflow Gates (16 existing assertions) — Phase ordering, agent spawn patterns, tool calls
  2. Producer/Consumer Contracts — JSON files written by one phase are correctly read by the next
  3. Verification Scores — Real prism_interview MCP scores; findings without code evidence get low scores

Execution

Phase T0: Setup

  1. Read test cases from evals/evals.json (relative to this SKILL.md)
  2. Generate a test run ID: test-{short-id} via uuidgen | cut -c1-8
  3. Resolve paths:
    • {skill-dir} = absolute path to this SKILL.md's parent directory
    • {analyze-skill-path} = resolve evals.json analyze_skill_path relative to {skill-dir} → absolute path
    • Ontology scope is auto-resolved by the MCP server from brownfield defaults (no manual mapping needed)
  4. Create workspace: ~/.prism/state/{test-run-id}/
  5. Create results directory: {skill-dir}/test-results/{test-run-id}/
  6. Show user: "Running {N} test cases. Estimated time: ~5-8 min per test case."

Phase T1: Execute Test Cases

For each test case in evals/evals.json:

T1.1: Spawn Analyze Orchestrator

Spawn a background agent that executes the full prism:analyze workflow. The agent must:

  • Read ../analyze/SKILL.md and follow it exactly
  • Use the test case's prompt as the analysis request
  • Use the test case's target_codebase as the code to analyze
  • Use state directory: ~/.prism/state/{test-run-id}/{eval-id}/
  • Auto-approve Phase 0.6 (skip AskUserQuestion — add instruction: "Auto-approve all perspectives without asking the user")
  • Execute Phase 2B verification using real prism_interview + prism_score MCP calls
  • Write all artifacts (seed-analysis.json, perspectives.json, context.json, findings.json, etc.)

Read the full file on GitHub · 194 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 194 lines · 96 tokens per session scan A b25c390852fd

Subscribe to this mod's changes

test-analyze is a skill published in the GitHub repository cohemm/prism (5 stars, last pushed 3mo ago), licensed MIT. It adds 96 tokens to every session and 1,894 once invoked, about $0.0005 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 2026-08-31.

Analytics and metricsTesting
Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens