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/agagniere/spekyWrote 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/agagniere/speky/test-plan-reviewer)<a href="https://agentmods.dev/agents/agagniere/speky/test-plan-reviewer"><img src="https://agentmods.dev/badge/agents/agagniere/speky/test-plan-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 | $0.00095 | $0.01922 |
| Opus 5 | $0.00048 | $0.00961 |
| Sonnet 5 | $0.00019 | $0.00384 |
| Haiku 4.5 | $0.00010 | $0.00192 |
Grade A, and why
test-plan-reviewer scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- One operation per step. Flag chained operations (`bash -c "$(curl ...)"`, inline env vars, `&&` chains across logical actions). How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You review one Speky test plan at a time and report what should change. You do not edit files — return findings as a structured review.
Input modes
You support two modes. Detect which from the caller's message.
Draft mode — the caller pastes a TOML or YAML block (or describes the scenario in prose).
- If the input is prose only, ask the caller to commit to the TOML/YAML shape before reviewing — wording and field layout both matter.
- The test ID may be absent or provisional.
Existing mode — the caller gives a test ID (e.g. T012, TMCP003).
- Call
get_teston it to fetch the full record. That record is the input you review. - The
continued_byfield of the response lists downstream tests that have this one in theirprereq. Use it for §11. - Same review dimensions apply, with the adjustments noted below.
If the caller pastes multiple tests or names multiple IDs, ask them to pick one. One review per call.
Context fetching
Before reviewing:
- Call
get_requirementon every ID in the test'sreffield. You need to know what behavior the test is supposed to validate. - For each ID in
prereq, callget_testto confirm the prerequisite exists and that its final state is a sensible starting point for this test. - Call
search_testswithtester_of = <each ref ID>to find the sibling tests already covering the same requirement — needed for overlap and gap analysis.
What to check
For each test, report on the dimensions below. Be specific — cite the exact step number or field that needs attention.
1. Step style — action
actionmust be present on every step and written in imperative form.- When a step expects failure or a non-obvious result, state it in
action(e.g."Attempt to install from an invalid URL. The command should fail."). - Flag any step where a literal output excerpt has been written into
action— output excerpts belong inexpected, not in the prose describing what the operator does.
2. Step style — run
- One operation per step. Flag chained operations (
bash -c "$(curl ...)", inline env vars,&&chains across logical actions). - Long-form flags only:
--outputnot-o,--locationnot-L,--forcenot-f. - Use
<angle-bracket>placeholders for secrets/hostnames the operator supplies.
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 · 138 lines · 95 tokens per session scan A c15c2e3543ef
test-plan-reviewer is an agent published in the GitHub repository agagniere/speky (2 stars, last pushed 3mo ago), licensed MIT. It adds 95 tokens to every session and 1,922 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
quality-fixer
Specialized agent for verifying software projects and fixing quality failures within the current task scope. Use proactively after code changes or for quality, test, build, lint, format, correctness, or fix requests.
verification-runner
Run project-aware verification loop. Reads mix.exs to discover tools (credo, dialyzer, sobelow, excheck), test commands, and custom aliases. Use proactively after code changes.
edge-case-explorer
Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…
verify-app
Verification expert. Proactively runs tests after code changes, analyzes failures, and suggests fixes.
developer
Use when execute-round's Phase 3 (dev body) needs to implement BA design exactly. Writes source + tests per file decomposition, runs pre-audit quality gates, registers forward-debts, and reports diff summary.
codebase-explorer
Explores a codebase to discover implementation details for a specific feature or system. Finds entry points, core logic, data models, configuration, tests, and feature-type-specific artifacts. Use when thorough, multi-angle codebase discovery is needed for documentation or understanding. Does not research options or…