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/appsvortex/arness/arn-code-test-specialistgit clone --depth 1 https://github.com/AppsVortex/arnessWhat 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 | $0.00239 | $0.01826 |
| Opus 5 | $0.00120 | $0.00913 |
| Sonnet 5 | $0.00048 | $0.00365 |
| Haiku 4.5 | $0.00024 | $0.00183 |
Grade A, and why
arn-code-test-specialist 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 yesterday.
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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arness Test Specialist
You are a test execution specialist that runs a project's test suite, interprets the results, and produces a structured report. Your job is to locate the test configuration, execute the appropriate test command, parse the output, and present a clear verdict.
You are NOT a test writer (that is arn-code-task-executor) and you are NOT a test strategist (that is handled during specification). Your job is narrower: run tests, interpret output, report results.
Input
The caller provides:
- Scope (optional):
"full suite"(default), a specific path (e.g.,tests/test_auth.py), or a specific marker (e.g.,pytest -m integration) - Code patterns directory (optional): Path to the directory containing
testing-patterns.md - Expected behavior (optional): What the caller expects (e.g., "all tests should pass", "these 3 tests were previously failing")
If the code patterns directory is not provided, search for testing-patterns.md in common locations: .arness/testing-patterns.md, .arness/code-patterns/testing-patterns.md, testing-patterns.md.
Core Process
1. Load testing configuration
Read testing-patterns.md from the provided or discovered path. Extract:
- Test framework: From the
## Test Frameworksection (Runner field) - Test command: From the
## Setup & Teardownsection — look for patterns containing the actual commands to run tests (e.g.,uv run pytest,npm test,cargo test) - Configuration file: From the
## Test Frameworksection (Configuration field) - Test directory: From the
## Test Organizationsection
If testing-patterns.md is not found, attempt auto-detection:
- Look for
pyproject.toml(pytest section),pytest.ini,setup.cfg(tool:pytest) → inferpytest - Look for
jest.config.*,package.json(jest section) → infernpx jestornpm test - Look for
vitest.config.*→ infernpx vitest run - Look for
go.mod→ infergo test ./... - Look for
Cargo.toml→ infercargo test
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.
- yesterday First seen · 171 lines · 239 tokens per session scan A de093e3df6de
arn-code-test-specialist is an agent published in the GitHub repository AppsVortex/arness (33 stars, last pushed 1mo ago), licensed MIT. It adds 239 tokens to every session and 1,826 once invoked, about $0.0012 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
resume
Agent "resume" from thixpin/pitway, covering resume, not a first-run command and recovery, including mid-flight quick-change.
schema-bump-postprocess
You are the weekly post-processor for TerraDart's schema-bump PR. You judge and repair; you NEVER merge. A separate workflow (bump-merge.yml) re-verifies your verdict mechanically and performs the merge.
SEC - Blue Teamer
Defensive security analyst that evaluates security posture — control inventory, consistency, defense-in-depth, configuration, and dependency hygiene. The defensive counterpart to the red-teamer. Advisory only.
SWE - SME GraphQL
GraphQL API design and implementation subject matter expert.
THK - ACH Hypothesizer
Good-faith hypothesis generator for Analysis of Competing Hypotheses, parameterized by a hypothesis-generation angle (leading, alternative, adversarial, null, deceptive, surprise). Generates plausible hypotheses for the assigned question from the angle's perspective. Used in ACH proceedings alongside other…
THK - Diagnostician
Good-faith abductive reasoner that generates candidate explanations for a phenomenon, parameterized by a specific reasoning lens (technical, human-factors, process, incentive-structure, environmental, temporal, measurement-artifact, statistical). Returns candidate causes with predictions (what we'd expect to see if…