aget: Skill for Claude Code

.claude/skills/aget-run-tests/SKILL.md

aget-run-tests is a skill for Claude Code from aget-framework/aget. It costs 10 tokens per session (518 once invoked), scanned A, original, Apache-2.0.

A test-running skill that detects common project test frameworks, runs the relevant tests, and summarizes the results.

In plain words
What is it for?
Running Python, JavaScript, Go, and other supported test suites, including unit, integration, conformance, or selected tests.
Why use it?
It turns raw test output into pass, failure, skip, duration, coverage, and actionable failure details.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is aget-framework/aget's own configuration. It tells Claude Code how to work on aget itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything aget configures →

Reuse

Borrowing it

Nothing to install: this file belongs to aget-framework/aget. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/aget-framework/aget/main/.claude/skills/aget-run-tests/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/aget-framework/aget

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.

agentmods badge for aget-run-tests

README.md
[![agentmods](https://agentmods.dev/badge/skills/aget-framework/aget/aget-run-tests.svg)](https://agentmods.dev/skills/aget-framework/aget/aget-run-tests)
Your own site
<a href="https://agentmods.dev/skills/aget-framework/aget/aget-run-tests"><img src="https://agentmods.dev/badge/skills/aget-framework/aget/aget-run-tests.svg" alt="Measured on agentmods" height="20"></a>
Per session 10 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 518 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00010 $0.00518
Opus 5 $0.00005 $0.00259
Sonnet 5 $0.00002 $0.00104
Haiku 4.5 $0.00001 $0.00052

Measured 6d ago against content hash a20b97afcf96, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

aget-run-tests 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 6d 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/aget-run-tests/SKILL.md · 98 lines

What it actually says

aget-run-tests

Execute test suites and report results. Supports unit tests, integration tests, and conformance tests with framework auto-detection.

Instructions

When this skill is invoked:

  1. Detect Test Framework

    • Check for pytest (pytest.ini, pyproject.toml)
    • Check for jest (package.json with jest)
    • Check for go test (go.mod)
    • Check for other common frameworks
  2. Execute Tests

    • Run with appropriate verbosity
    • Capture timing information
    • Handle test scope (all, unit, integration, specific)
  3. Process Results

    • Count pass/fail/skip
    • Capture failure details
    • Note coverage if available
  4. Report Findings

    • Summary statistics
    • Failure details with location
    • Actionable next steps

Execution Commands

# Python (pytest)
python3 -m pytest -v [path]

# JavaScript (jest)
npm test -- --verbose

# Go
go test -v ./...

# Python (unittest)
python3 -m unittest discover -v

Output Format

## Test Results

### Summary

| Metric | Value |
|--------|-------|
| Total | [N] |
| Passed | [N] |
| Failed | [N] |
| Skipped | [N] |
| Duration | [Xs] |
| Coverage | [N%] (if available) |

### Status: [PASS/FAIL]

### Failures (if any)

#### [Test Name]
- **File**: [path:line]
- **Expected**: [value]
- **Actual**: [value]
- **Error**: [message]

### Next Steps

1. [Action to fix failures]

Constraints

  • C1: NEVER modify test files during execution — test execution is read-only
  • C2: NEVER suppress test failures — all failures must be visible
  • C3: NEVER run tests with side effects without user consent — integration tests may modify state
  • SKILL-022: aget-run-tests specification
  • ONTOLOGY_developer.yaml: Test, Unit_Test, Test_Result concepts
  • CAP-DEV-001: Test Execution capability
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. 6d ago First seen · 98 lines · 10 tokens per session scan A a20b97afcf96

Subscribe to this mod's changes

aget-run-tests is a skill published in the GitHub repository aget-framework/aget (11 stars, last pushed today), licensed Apache-2.0. It adds 10 tokens to every session and 518 once invoked, about $0.0001 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.