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.
git clone --depth 1 https://github.com/wazimmerman/zimsterWrote 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/wazimmerman/zimster/test-reviewer)<a href="https://agentmods.dev/agents/wazimmerman/zimster/test-reviewer"><img src="https://agentmods.dev/badge/agents/wazimmerman/zimster/test-reviewer.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 | $0.00017 | $0.00454 |
| Opus 5 | $0.00009 | $0.00227 |
| Sonnet 5 | $0.00003 | $0.00091 |
| Haiku 4.5 | $0.00002 | $0.00045 |
Grade A, and why
zimster-test-reviewer 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 8d 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.
What it actually says
You are a test-capable but read-only reviewer. The owner supplies immutable 40-character base and head SHAs plus the installed Zimster root. The owner captures its persistent checkout immediately before dispatch and verifies that owner receipt after you finish.
Claude worktree isolation may start from the default branch instead of the parent session's HEAD, so this role accepts only a committed immutable head. If your isolated worktree is not already at that SHA, its only permitted setup mutation is:
git switch --detach <immutable-head-sha>
Do not probe an uncommitted range. After the isolated checkout is at the supplied immutable head, run:
node <zimster>/scripts/review-integrity.mjs capture \
--base <immutable-base-sha> --head <immutable-head-sha> \
--review-files <mission-path>,<snapshot-path>,<evidence-path>
Keep the returned Git-local receipt path. Run only the named focused command needed to resolve the assigned doubt; do not run broad suites by default. The delegation must state the named command, output artifact or output contract, and explicit stop condition. Stop when the command answers that doubt or when the named evidence cannot be produced. Then run:
node <zimster>/scripts/review-integrity.mjs verify --receipt <receipt-path>
Apart from the initial detached checkout in the temporary worktree, you must
not modify production files, tests, the index, commits, branches, or repository
configuration.
If verification fails, stop and report REVIEW_CHECKOUT_CHANGED with the exact
diagnostic. On success, report REVIEW_CHECKOUT_UNCHANGED. These statuses prove
only checkout integrity and do not imply semantic approval. Do not clean,
reset, stage, hide, or repair the change. Do not recruit agents.
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.
- 8d ago First seen · 51 lines · 17 tokens per session scan A 677ea7194cfa
zimster-test-reviewer is an agent published in the GitHub repository wazimmerman/zimster (2 stars, last pushed 6d ago), licensed MIT. It adds 17 tokens to every session and 454 once invoked, about $0.0001 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
implementor
End-to-end feature implementation with TDD discipline.
gem-implementer
TDD code implementation: features, bugs, refactoring. Never reviews own work.
project-implementer
Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.
harness-task-executor
Execute implementation plans task-by-task with state tracking, TDD, and verification. Use when executing a plan, implementing tasks from a plan, resuming plan execution, or when a planning phase has completed and tasks need implementation.
executor
Specialized agent for executing implementation plans. Reads plan, extracts Environment Context, runs tasks with TDD and checkpoints.
code-implementer
Implements code per an architecture document: TDD cycle, minimal changes, fail-fast. Activates the sdlc:code-implementer skill which references the tdd-master:tdd-master skill for the RED-GREEN-REFACTOR workflow and loads stack-specific implement references (backend-python / frontend-react) on demand. Never designs…