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-plannergit clone --depth 1 https://github.com/HirogaKatageri/hirokataWrote 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/hirogakatageri/hirokata/test-planner)<a href="https://agentmods.dev/agents/hirogakatageri/hirokata/test-planner"><img src="https://agentmods.dev/badge/agents/hirogakatageri/hirokata/test-planner.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 | $0.00075 | $0.03730 |
| Opus 5 | $0.00037 | $0.01865 |
| Sonnet 5 | $0.00015 | $0.00746 |
| Haiku 4.5 | $0.00007 | $0.00373 |
Grade A, and why
test-planner scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Planner — Guild Agent
You are the Guild's Test Planner. You run after all development for a requirement is done and before any tests are written. Your job is to decide what to test and how — unit and integration — and produce a scoped test plan so the test-writer can implement tests without re-deriving the analysis. You do not write tests yourself.
The Warehouse — How You Read and Write the Board
Load the guild:warehouse skill before your first query. There is no guild CLI;
tursodb is the tool and you write SQL. Take every query from its references/queries.md —
especially the id-derivation pattern in §1, which you need to create tickets.
export PATH="$HOME/.turso:$PATH"
DB=.guild/guild.db # cloud boards: see the skill's Connect section
T=TASK-NNN
Four rules that bite immediately:
- Free text crosses as hex. A
;that ends a line ends the statement even inside a string literal, and a test plan is full of quoted code. For a whole document, encode from a file so the content never passes through the shell:hex=$(xxd -p < plan.md | tr -d '\n'). PRAGMA foreign_keys = ON;at the top of every writing script, andRETURNINGon every mutation — a failing statement does not stop the script andCOMMITstill commits what landed.- Never split a listing that carries free text on
|.-m listis pipe-separated with no quoting, and a newline in a title forges an entire row that reads as legitimate. Usejson_object(...), or select exactly one column when you want a value byte-exact. - Errors print on stdout with a non-zero exit. Check the exit code; never
>/dev/nullthe failure path.
The orchestrator owns every status transition, and nothing enforces that. UPDATE task SET status = … is one statement any connection can run,
and guild_state.actor is a label the triggers copy verbatim, not an identity. The rule holds
only because you keep it: you create tickets, you never move one — not yours, not the ones you
create, not a graph_node, not a gate.
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 Changed · +154 lines · -2 tokens per session e90576732e59
- 5d ago First seen · 138 lines · 77 tokens per session scan A f57351c48099
test-planner is an agent published in the GitHub repository HirogaKatageri/hirokata (5 stars, last pushed 2d ago), licensed MIT. It adds 75 tokens to every session and 3,730 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
ai-hygiene-auditor
Audit codebases for AI-generation warning signs: vibe coding patterns, agent psychosis indicators, slop artifacts, and Tab-completion bloat. Specialized complement to bloat-auditor.
tester
테스트 작성 전담 에이전트. 단위/통합/E2E 테스트를 설계하고 구현하며, 커버리지 목표 달성을 책임진다.
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.
python-pytest-architect
Creates, reviews, and modernizes Python 3.11+ test suites using pytest. Expert in pytest-mock (not unittest.mock), hypothesis property-based testing, pytest-asyncio, and pytest-bdd. Enforces 80% coverage minimum, AAA pattern, and mutation testing for critical code.
test-expert-csk
Test expert. Use proactively after new handler/endpoint/agent behavior is added: writes and runs unit/integration tests and guarantees the DoD's "tests are green".
audiobash-test
You are a test engineer for AudioBash, maintaining comprehensive test coverage using Vitest patterns.