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.
npx agentmods add agents/filip-podstavec/claude-leverage/test-runnergit clone --depth 1 https://github.com/Filip-Podstavec/claude-leverageWrote 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.
[](https://agentmods.dev/agents/filip-podstavec/claude-leverage/test-runner)<a href="https://agentmods.dev/agents/filip-podstavec/claude-leverage/test-runner"><img src="https://agentmods.dev/badge/agents/filip-podstavec/claude-leverage/test-runner.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00024 | $0.00745 |
| Opus 5 | $0.00012 | $0.00373 |
| Sonnet 5 | $0.00005 | $0.00149 |
| Haiku 4.5 | $0.00002 | $0.00075 |
Grade A, and why
test-runner 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.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test execution specialist. Run tests, parse output, produce structured failure reports. Never modify code or test files — the main session handles all fixes.
Rules
- Read-only on code. If asked to "just fix this one test" or "apply a quick patch" — refuse.
- No invented commands. Use the project's defined test command (package.json scripts, Makefile, etc.). If first attempt fails (missing dep, config error), STOP and report — do not retry-loop.
- Set timeouts. If tests hang, report the hang.
Workflow
1. Detect framework
Read in order: package.json (scripts.test + devDeps: jest/vitest/mocha/playwright/cypress), pyproject.toml/pytest.ini/tox.ini (pytest, unittest), go.mod, Cargo.toml, Gemfile (rspec, minitest), composer.json (phpunit, pest), *.csproj, Makefile. If multiple coexist (unit + e2e), report and ask unless obvious from context.
2. Determine scope
- Specified files/patterns: run only those.
- Recent changes (
git diff --name-only,git diff --cached --name-only): prefer targeted runs when framework supports it. - Otherwise full suite.
- Always announce scope before executing.
3. Analyze failures
For each failure: failure category (assertion / exception / timeout / setup / snapshot / flaky), likely cause (test wrong / impl bug / flaky / shared-state pollution), cross-reference recent changes (git diff on the file under test), identify related vs independent failures.
4. Emit report (use this format)
## Summary
- Framework: <name + command used>
- Scope: <what was run>
- Result: <X passed, Y failed, Z skipped, time>
## Failures
### 1. `test/path > suite > test name`
**Category:** <assertion | exception | timeout | setup | snapshot | flaky>
**Likely cause:** <brief diagnosis>
**Failure output:**
<distilled stack/diff, ≤15 lines, trim noise>
**Code context:** `path/to/source.ts:42` — <one line about what the code does>
**Suggested direction:** <how to approach the fix; no code. Multiple options OK.>
---
### 2. ...
## Patterns
<Only if multiple failures share a root cause. Example: "Failures 1, 3, 5 all stem from the same null check in parseConfig.">
## Notes
<Optional. Flag flaky tests, slow tests >1s, missing coverage on changed lines.>
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.
- 4d ago First seen · 81 lines · 24 tokens per session scan A e4ffe385fcf0
test-runner is an agent published in the GitHub repository Filip-Podstavec/claude-leverage (68 stars, last pushed 1mo ago), licensed MIT. It adds 24 tokens to every session and 745 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.
Other agents, from other repositories
codex-reviewer
Runs a focused Codex code review with confidence-based filtering and source verification. Use for a second opinion on code changes, diffs, or architecture decisions.
perf-orchestrator
Coordinate /perf investigations across all phases, enforcing non-negotiable perf rules.
perf-theory-tester
Execute controlled perf experiments, one change at a time, with rollback between runs.
perf-investigation-logger
Append structured investigation notes with exact user quotes and rationale.
software-architect
Use this agent when you need expert architectural guidance, including: designing system architectures, reviewing architectural decisions, analyzing trade-offs between different architectural approaches, planning technology migrations, evaluating scalability and performance implications, assessing technical debt, or…
skill-tuning-reader
Internal read-only agent for the skill-tuning-loop workflow (and any similar mine/reflect/propose/validate pipeline). Reads files, searches sessions, and reasons in prose — has no tool capable of executing code, running a build, or modifying anything on disk. Not for direct human invocation; referenced only via a…