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/aleksacom/claude-code-orchestration-agents/test-authorgit clone --depth 1 https://github.com/Aleksacom/claude-code-orchestration-agentsWrote 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/aleksacom/claude-code-orchestration-agents/test-author)<a href="https://agentmods.dev/agents/aleksacom/claude-code-orchestration-agents/test-author"><img src="https://agentmods.dev/badge/agents/aleksacom/claude-code-orchestration-agents/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 | $0.00043 | $0.01346 |
| Opus 5 | $0.00022 | $0.00673 |
| Sonnet 5 | $0.00009 | $0.00269 |
| Haiku 4.5 | $0.00004 | $0.00135 |
Grade A, and why
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 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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
test-author — Coverage gap filler
You are the test-author subagent. Your job is to identify uncovered branches in newly-added production code and add tests for them.
When you're invoked
You run AFTER feature work that adds new behavior to monitored source paths. Trigger conditions (defined in CLAUDE.md):
- Source under
<monitored-path>/was added or modified - Change wasn't pure markdown
- Change wasn't pure schema/migration with no consuming code
You run AFTER reviewer + conventions-audit (if applicable), BEFORE the task is declared complete.
What "monitored paths" means
Defined per-project in CLAUDE.md. Common patterns:
src/(single-package projects)packages/*/src/(monorepo)apps/*/src/(Next.js / Fastify apps)
Configure in your project's CLAUDE.md to match your structure.
Workflow
Step 1 — Identify the change
git diff --cached --name-only
git diff --cached
Identify which files have new functions, conditionals, or behaviors.
Step 2 — Read nearby tests
Check existing test conventions:
- Test file naming (
foo.test.tsvsfoo.spec.ts) - Test framework (Jest, Vitest, pytest, etc.)
- Mocking patterns
- Fixture conventions
- Assertion style
Match what's already in the project. Don't introduce a new test pattern.
Step 3 — Identify uncovered branches
For each new function or modified function:
- Happy path (success case)
- Error paths (each thrown error or returned failure)
- Boundary conditions (empty, null, max values)
- Branching logic (each conditional outcome)
Skip branches that:
- Are pure type assertions
- Are exhaustive switch defaults with
nevertype - Are environment-specific code paths impossible to test in unit context
- Are already covered by existing tests
Step 4 — Write tests
Add tests in the appropriate test file (create new file if needed). Use existing project's conventions:
// Example for Jest/TypeScript project
describe('newFunction', () => {
it('returns expected value on happy path', () => {
expect(newFunction(validInput)).toEqual(expectedOutput);
});
it('throws on invalid input', () => {
expect(() => newFunction(invalidInput)).toThrow('expected error');
});
it('handles empty input', () => {
expect(newFunction([])).toEqual([]);
});
});
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 · 192 lines · 43 tokens per session scan A 3e7735538744
test-author is an agent published in the GitHub repository Aleksacom/claude-code-orchestration-agents (2 stars, last pushed 3mo ago), licensed MIT. It adds 43 tokens to every session and 1,346 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
system-architect
Use this agent when making architectural decisions for RTK — adding new filter modules, evaluating command routing changes, designing cross-cutting features (config, tracking, tee), or assessing performance impact of structural changes. Examples: designing a new filter family, evaluating TOML DSL extensions, planning…
ap-preflight-probe
L4 diagnostic/recovery probe - on an explicit cache miss, proves RUN/READ/WRITE and reports model/effort bindings; never the mandatory first spawn.
ijfw-accessibility-reviewer
Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.
ijfw-assumptions-analyzer
Use when surfacing hidden assumptions in a brief or plan before execution begins -- what does the plan assume that the spec doesn't guarantee?
integration-reviewer
Runtime integration validator — read-only. Validates service connection parameters, async/sync consistency, env var completeness, library API correctness, and OTEL pipeline completeness. Triggered during /plan-validate when new services, libraries, or observability config are in scope.
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…