test

A command that runs a project’s tests and examines any failures.

In plain words
What is it for?
Use it to detect the project’s test setup, run tests, summarize results, and explain failed tests with likely fixes.
Why use it?
It removes the need to work out the test command and interpret every failure manually.

Command

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.

agentmods
npx agentmods add commands/rileyhilliard/agentrc/test
Clone the repo
git clone --depth 1 https://github.com/rileyhilliard/agentrc
Per session 5 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 275 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
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 $0.00005 $0.00275
Opus 5 $0.00003 $0.00138
Sonnet 5 $0.00001 $0.00055
Haiku 4.5 $0.00001 $0.00028

Measured 2d ago against content hash ebe1e385dc1c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

test scanned grade B with 1 finding 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.

Unrestricted tool accessmediumExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

**DELEGATION ONLY**: Do NOT run any commands or investigate the codebase yourself. Your only job is to immediately invoke the `ce:haiku` agent via Task tool, passing the prompt template below with `$ARGUMENTS` substitute
.agentrc/commands/test.md · 39 lines

What it actually says

DELEGATION ONLY: Do NOT run any commands or investigate the codebase yourself. Your only job is to immediately invoke the ce:haiku agent via Task tool, passing the prompt template below with $ARGUMENTS substituted.

Task Prompt for Haiku Agent

Run tests and analyze any failures.

User arguments: $ARGUMENTS
(If provided, use as the test command. Otherwise, auto-detect.)

**Step 1: Detect the test command** (if no custom command provided)
- Check for package.json (yarn test or npm test)
- Check for pytest.ini or setup.py (pytest)
- Check for Cargo.toml (cargo test)
- Check for Makefile with test target
- Check for go.mod (go test ./...)

**Step 2: Run the tests**
Execute the detected or provided test command.

**Step 3: Analyze failures** (if any occur)
- Parse the failure messages
- Identify root causes
- Reference specific file:line locations
- Suggest fixes

**Step 4: Report results**
Provide a summary including:
- Total tests run
- Passed/failed/skipped counts
- For failures: clear, actionable feedback
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. 2d ago First seen · 39 lines · 5 tokens per session scan B ebe1e385dc1c

Subscribe to this mod's changes

test is a command published in the GitHub repository rileyhilliard/agentrc (3 stars, last pushed 6mo ago), licensed MIT. It adds 5 tokens to every session and 275 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.