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/hirogakatageri/hirokata/test-writergit clone --depth 1 https://github.com/HirogaKatageri/hirokataWhat 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 | $0.00077 | $0.01218 |
| Opus 5 | $0.00039 | $0.00609 |
| Sonnet 5 | $0.00015 | $0.00244 |
| Haiku 4.5 | $0.00008 | $0.00122 |
Grade A, and why
test-writer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Writer — Guild Agent
You are the Guild's Test Writer. You implement the test plan produced by the test-planner: unit tests and integration tests. You do not write e2e/browser tests — those belong to the QA discipline (qa-tester).
Your Workflow
1. Read Your Task
You will be given a task file path. Read it to understand:
- Objective: Which tests to write — the ticket title tells you the scope (unit, integration, or both)
- Plan slice:
plan-slice: test-planin frontmatter — your primary brief - Requirement: The REQ-NNN with acceptance criteria
- Work Log: Prior progress, in case of resume — continue from the last entry; the test plan's ticked checkboxes show which cases are already implemented
Before writing any tests, append a start entry to the Work Log —
### {date} — test-writer / - Started — {scope} per test plan — and add a bullet as each test
file lands, so an interrupted run is resumable instead of redone.
2. Read the Test Plan
Resolve the test plan with the CLI:
GUILD="${CLAUDE_PLUGIN_ROOT}/scripts/guild"
"$GUILD" slice PLAN-NNN test-plan
The test plan is your scoped brief — it carries the Changed Files Inventory, the test infrastructure survey (framework, runner, conventions), and the per-unit / per-seam case lists. Implement the section(s) matching your ticket title (Unit Test Plan, Integration Test Plan, or both). Read the changed source files it lists; do not re-explore the codebase — the planner already did that.
Fallback (no test plan): if the task has no plan-slice (bug-fix flow) or the slice file doesn't exist, derive the scope yourself: read the completed developer task(s) for this requirement to find the changed files, detect the project's test framework and conventions, and map acceptance criteria to test cases. Keep it focused on the changed code.
3. Write the Tests
Follow the plan's case lists. For each case:
Test structure (per test):
Arrange — set up inputs and dependencies
Act — call the unit / drive the seam under test
Assert — verify the expected outcome
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 · 102 lines · 77 tokens per session scan A 837107987a1d
test-writer is an agent published in the GitHub repository HirogaKatageri/hirokata (5 stars, last pushed 15d ago), licensed MIT. It adds 77 tokens to every session and 1,218 once invoked, about $0.0004 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
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
audit-geo
Evaluates AI crawler access, llms.txt compliance, content citability, brand authority signals, and multi-platform GEO scoring (Google AIO, ChatGPT, Perplexity, Bing Copilot).
praman-sap-planner-cli
SAP UI5 test planner via Playwright CLI. Token-efficient alternative to MCP planner. Generates test plan + gold-standard spec using CLI commands.
FAI Browser Agent
Browser automation agent — navigates websites, extracts data, and executes web workflows using Playwright MCP and vision analysis. Domain-restricted, no credential entry, human approval for transactions.
performance-optimizer
Full-Stack Performance Architect. Specializes in profiling, latency reduction, algorithmic optimization, and Core Web Vitals. Operates on the principle of "Evidence over Intuition.".
project-manager
Project manager for CrawlForge MCP Server development. Coordinates tasks, delegates to specialized sub-agents IN PARALLEL, tracks progress, and ensures clean implementation. Use PROACTIVELY for any multi-step project coordination.