test-harness

test-harness is a skill for Claude Code from zernie/vigiles. It costs 103 tokens per session (2,611 once invoked), scanned A, original, MIT.

A testing skill for Claude Code setups, including hooks, skills, agents, settings, and CLAUDE.md instructions. It uses three levels of testing, from simple checks to tests involving a real language model.

In plain words
What is it for?
Checking that hooks allow or block events, skills trigger, injected instructions reach the model, and a complete Claude Code setup works together.
Why use it?
It helps determine whether an agent setup is assembled correctly and behaves as intended, without using a paid model when a simpler test is enough.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

Part of the vigiles plugin — 26 skills, 4 hooks, 2 plugins shipped together

not rated 15repo changed 4d ago A scan Socket: passSnyk: passSkillSpector: warn 103 tokens original MIT

Good fit Checking that hooks allow or block events, skills trigger, injected instructions reach the model, and a complete Claude Code setup works together.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zernie/vigiles/test-harness
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 zernie/vigiles --skill test-harness
Clone the repo
git clone --depth 1 https://github.com/zernie/vigiles

Made for: Claude Code.

Or install vigiles, the plugin that ships this one along with the rest of its 26 skills, 4 hooks, 2 plugins.

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-harness

README.md
[![agentmods](https://agentmods.dev/badge/skills/zernie/vigiles/test-harness.svg)](https://agentmods.dev/skills/zernie/vigiles/test-harness)
Your own site
<a href="https://agentmods.dev/skills/zernie/vigiles/test-harness"><img src="https://agentmods.dev/badge/skills/zernie/vigiles/test-harness.svg" alt="Measured on agentmods" height="20"></a>
Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,611 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
  • Socket pass 31 Aug 2026
  • Snyk pass 31 Aug 2026
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 6 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Prompt Injection · line 20
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 20
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 22
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium MCP Rug Pull · line 105
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 106
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 121
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
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 $0.00103 $0.02611
Opus 5 $0.00051 $0.01306
Sonnet 5 $0.00021 $0.00522
Haiku 4.5 $0.00010 $0.00261

Measured 4d ago against content hash 45d33e5a4881, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

test-harness 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-harness/SKILL.md · 176 lines

How it starts

The opening of the file, as written. The whole thing — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test the Claude Code harness — the hooks, skills, settings, and CLAUDE.md that steer an agent — as the assembled machine it ships as. vigiles gives three tiers, cheapest first; this skill picks the right one, writes the test, and runs it.

The guiding rule: start at the cheapest tier that can answer the question, and climb only when it genuinely can't. Two of the three tiers need no model and no API key, so they run on every commit for free — reach for the paid real-model tier only when the question actually requires a real model.

Step 0 — Pick the tier (the judgment call)

Match what you're testing to the cheapest tier that can answer it:

What you're testing Tier Cost API
"Does this hook block/allow event X?" — pure hook logic, every event type (incl. Edit/Write, PreCompact, SessionEnd, SubagentStop) Unit free, milliseconds, no claude runHook
"Is the hook actually wired into the assembled plugin and does it fire in a real session?" Deterministic free, no API key (real claude + scripted mock) runHarnessTest + scriptModel
"Did the injected context (a SessionStart hook, a /command) actually reach the model?" Deterministic free, no API key runHarnessTesttrace.modelRequests / assertRequestContains
"Does this skill's description trigger when it should (recall) and stay quiet when it shouldn't (precision)?" Eval paid (real model) measureTriggerRate (+ irrelevantPrompts) → assertTriggerRate({ min, maxFalsePositive })
"Can I measure triggering on a cheaper model and trust it as a floor?" Eval paid (two runs) compareContainment(weak, strong)formatContainment
"Is this exact skill's output any good?" — absolute quality, no on/off baseline (the default for testing one skill) Eval paid (real model) measure({ checks: [judged(rubric)] })assertRates({ min })
"Does this harness change move what the agent does, relative to off?" — A/B lift, regression, signal vs noise Eval paid (real model) runEval (arms) + assertSignificant

Most harness questions — block/allow, wired-in, context-landed — never need a model. Only "does the model trigger / behave differently" needs the eval tier.

⚠️ A trigger-rate of 0% on EVERY prompt is a wiring bug until proven otherwise. It reads like a verdict on the description, and three separate setup mistakes produce it: a bare id in fired where the namespaced <plugin>:<skill> is required; pluginDir where a loose .claude/skills needs skillsDir; and a missing fixture, since a run starts in an empty directory and a prompt about a file that isn't there is one the model is right to decline. Rule all three out before reporting it. (A partial rate is a real number — don't second-guess it.)

Read the full file on GitHub · 176 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 Changed · -212 lines 45d33e5a4881
  2. 8d ago First seen · 388 lines · 103 tokens per session scan A 50b54c4e3ac1

Subscribe to this mod's changes

test-harness is a skill published in the GitHub repository zernie/vigiles (15 stars, last pushed today), licensed MIT. It adds 103 tokens to every session and 2,611 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 2026-08-30.