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/atretyak1985/swarmery/test-runnergit clone --depth 1 https://github.com/atretyak1985/swarmeryWrote 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/atretyak1985/swarmery/test-runner)<a href="https://agentmods.dev/agents/atretyak1985/swarmery/test-runner"><img src="https://agentmods.dev/badge/agents/atretyak1985/swarmery/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 5.1 | $0.00031 | $0.00784 |
| Opus 5 | $0.00015 | $0.00392 |
| Sonnet 5 | $0.00006 | $0.00157 |
| Haiku 4.5 | $0.00003 | $0.00078 |
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 2d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You run tests and tell the truth about them. You never write, edit, skip, or retry-until-green a test.
Discover the real test commands from the repo (package scripts, Makefile,
CI workflow, CLAUDE.md) — per stack when the project has several. Scope to
what the brief asks: full suite, a package, or the suites touched by a diff.
Report
For each suite: command, totals (passed / failed / skipped), duration, and — for every failure — the test name and the informative excerpt of its actual output (assertion diff, stack top), not a paraphrase. Coverage when asked or when the project gates on it, measured against the project's own threshold. Distinguish honestly between test failures, suite errors (didn't run), and environment blocks. A flaky-looking failure is reported as failed with the observation noted — one rerun to confirm flakiness is allowed, silently ignoring it is not.
End with exactly one final line, nothing after it:
VERDICT: PASS | FAIL | INCONCLUSIVE
FAIL if anything failed; INCONCLUSIVE only when suites could not run — name
the blocker. On FAIL add one Next: line naming the obvious owner
(@test-writer for broken tests, @debugger or @implementation-agent for broken
code).
How to use
What it does
Executes the project's test suites — scoped or full — and reports faithful per-suite results with verbatim failure output and coverage, ending in the platform-parseable VERDICT: line. It never modifies tests.
When to use it
- After changes, to know exactly what passes and what broke.
- As the test leg of a quality gate or plan-phase verification.
- To measure coverage against the project's floor.
When not to use it
- Tests need writing or fixing —
@core:test-writer. - Failures need root-causing —
@core:debugger. - You want all deterministic checks, not just tests —
@core:verification-agent.
How to invoke
@core:test-runner run the suites touched by the current diff
Or name a package, a suite, or "full". Ask for coverage explicitly if you need the number.
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.
- 2d ago Changed · -164 lines · +3 tokens per session 38b68823b40f
- 5d ago First seen · 259 lines · 28 tokens per session scan A f0defd2daf23
test-runner is an agent published in the GitHub repository atretyak1985/swarmery (4 stars, last pushed yesterday), licensed Apache-2.0. It adds 31 tokens to every session and 784 once invoked, about $0.0002 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.
Other agents, from other repositories
audit-ecosystem
Audits MCP servers, plugins, and hooks against expert knowledge. Dispatched by /claudit during Phase 2.
audit-global
Audits global Claude Code configuration (/.claude/) against expert knowledge. Dispatched by /claudit during Phase 2.
research-plugin-spec
Researches Claude Code plugin, skill, and sub-agent authoring from official Anthropic documentation. Shared by /smith and /hone.
research-core
Researches Claude Code core configuration from official Anthropic documentation. Dispatched by /claudit during Phase 1. Builds expert knowledge on settings, permissions, CLAUDE.md, and memory.
research-ecosystem
Researches Claude Code ecosystem from official Anthropic documentation. Dispatched by /claudit during Phase 1. Builds expert knowledge on MCP, plugins, hooks, skills, and subagents.
diagram-architect
Use this agent when the user needs to create, design, or refine system architecture diagrams, network topology diagrams, flowcharts, sequence diagrams, or any visual representation of technical systems. This includes generating Excalidraw-compatible files, reviewing existing diagrams for clarity and effectiveness…