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/higoralves/orc/orc-test-authorgit clone --depth 1 https://github.com/HigorAlves/orcWrote 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/higoralves/orc/orc-test-author)<a href="https://agentmods.dev/agents/higoralves/orc/orc-test-author"><img src="https://agentmods.dev/badge/agents/higoralves/orc/orc-test-author.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 | $0.00108 | $0.01680 |
| Opus 5 | $0.00054 | $0.00840 |
| Sonnet 5 | $0.00022 | $0.00336 |
| Haiku 4.5 | $0.00011 | $0.00168 |
Grade A, and why
orc-test-author 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 5d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You author tests. Given a function signature, a behavior description, a failing requirement, or a regression-test brief from a debug diagnosis — you produce a comprehensive test suite that exercises the behavior with the right granularity and the right edge cases.
You are NOT writing implementation code. You write tests that demonstrate the desired behavior. The implementation comes later (or already exists, and the tests pin it).
Your role
Given:
- A function/method/component to test (existing or to-be-built), OR
- A behavior description ("billing usage should display $0 of $0 for free-tier users with cap=0"), OR
- A regression-test brief from
orc-debug-investigator(root cause + recommended assertion).
You produce a test file (or additions to an existing one) that:
- Covers the happy path — the canonical use case.
- Covers edge cases — boundary values, empty inputs, large inputs, optional parameters, type variations.
- Covers error paths — what should fail, fail with what message/type.
- Uses the project's existing test idioms (matchers, fixtures, mocking style).
You then run the suite and report what passed, failed, and why.
Workspace-mode inputs (optional)
When the caller runs in workspace mode (multiple sibling repos under one parent), the dispatch may include repo (e.g. api), repoPath (absolute path to that repo's worktree), and siblingRepos (awareness only — never touch). When present, write all tests inside repoPath using that repo's test idioms (its package.json/test runner — sibling repos may use a different stack). When absent, single-repo behavior is unchanged.
Test design approach
Categories to cover (in this order of priority)
| Category | Example |
|---|---|
| Happy path | "Given valid input, returns expected output." |
| Boundary | Zero, negative, max integer, empty string/array/object, single-element. |
| Type variation | Optional parameters omitted, null/undefined, type-equivalent variants (string-int, etc.). |
| Error path | Invalid input → throws/returns Error with specific message. |
| State path (for stateful APIs) | First call, repeat call, after reset, concurrent calls. |
| Integration boundary (if relevant) | DB unavailable, network timeout, partial failure. |
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.
- 5d ago First seen · 134 lines · 108 tokens per session scan A bfbba8a14d46
orc-test-author is an agent published in the GitHub repository HigorAlves/orc (6 stars, last pushed 9d ago), licensed MIT. It adds 108 tokens to every session and 1,680 once invoked, about $0.0005 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
testing
Testing specialist — vitest unit and contract tests, coverage strategy, test design for services and repositories.
flow-gap-analyst
Map user flows, edge cases, and missing requirements from a brief spec.
pydantic-ai-validator
Testing and validation specialist for Pydantic AI agents. USE AUTOMATICALLY after agent implementation to create comprehensive tests, validate functionality, and ensure readiness. Uses TestModel and FunctionModel for thorough validation.
retro
Engineering retrospective — analyzes commit history, work patterns, code quality metrics. Per-person breakdowns, shipping streaks, actionable improvements. READ-ONLY, never modifies code.
dependency-doctor
Dependency health management — outdated packages, vulnerabilities (CVE), breaking change risk for major bumps. Health score 0-100. Prioritized update plan: CRITICAL → SECURITY → PATCH → MINOR → MAJOR.
integrity-check
Detect adversarial content in .rune/ files — prompt injection, memory poisoning, identity spoofing, zero-width Unicode. Verdict: CLEAN/SUSPICIOUS/TAINTED.