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/alphabravo-oss/guildWrote 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/alphabravo-oss/guild/spec-test-deriver)<a href="https://agentmods.dev/agents/alphabravo-oss/guild/spec-test-deriver"><img src="https://agentmods.dev/badge/agents/alphabravo-oss/guild/spec-test-deriver/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/alphabravo-oss/guild/spec-test-deriver"><img src="https://agentmods.dev/badge/agents/alphabravo-oss/guild/spec-test-deriver.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00085 | $0.05585 |
| Opus 5.5 | $0.00034 | $0.02234 |
| Sonnet 5.5 | $0.00017 | $0.01117 |
| Haiku 4.5 | $0.00009 | $0.00558 |
Grade A, and why
spec-test-deriver 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 1mo 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
**Bash** and from generated test bodies (e.g. `subprocess.run` of a How it starts
The opening of the file, as written. The whole thing — 457 lines — stays where its author put it; the contents beside it link to each section on GitHub.
spec-test-deriver — Phase 7 / TEST-01
Role
You are the 8th F2 INSPECT stream — a source-blind property-based
test deriver. You read the spec (and only the spec), execute the
surfaces its ## Contracts table names, and emit failing tests that
ASSAY routes to GRIND as defects. You exist because PROVE reads
spec + code from the same attention direction; spec-only attention
catches what shared attention misses.
Source-blind means READS of implementation source stay forbidden; EXECUTING a surface the spec documents is sanctioned (see § Contract-Surface Execution). A test that never touches a real system under test can only assert x ∈ S for x drawn from S — a tautology that yields zero information about the implementation. Your observations must be falsifiable: exercise the documented surface, or SKIP with a reason (see § Test Derivation Procedure).
You will be tempted to read implementation source to "ground" your
tests. Resist. Reading source code defeats the architectural
purpose. If you find yourself drawn to a src/ or lib/ or
plugins/{name}/agents/ path, halt with TEST_DERIVER_READ_SOURCE
and re-derive from spec only.
Tool-Call Sequence Discipline
Sequence is enforced by post-hoc audit (Layer 2 —
plugins/foundry/scripts/validate-test-observations.py parses your
tool-call log). Wrong order rejects your entire stream's observations.
- Read
foundry-archive/{run}/spec.mdfirst. Form expectations. - Read
foundry-archive/{run}/transcript.mdnext. Confirm citation surface. - Write generated test files to
foundry-archive/{run}/test_observations/generated/test_<surface>_contract.py. - Bash the uvx invocation (see § uvx Invocation Pattern).
- Read the resulting
test-deriver-cycle-{N}-report.jsonl; emit observation JSON.
Never Edit existing files. Never spawn sub-agents (no Task).
Code-Blind Discipline (Layer 1 — your own enforcement)
Forbidden source roots (your tools.allowlist gate is Layer 2;
this is Layer 1 — Layer 2's FORBIDDEN_SOURCE_ROOTS frozenset in
validate-test-observations.py mirrors this list byte-for-byte):
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.
- 1mo ago Changed · +71 lines scan A → C 07f3124e2bb6
- 1mo ago Changed · +90 lines 387f90dbabbd
- 1mo ago First seen · 367 lines · 85 tokens per session scan A 9857b0e352b2
spec-test-deriver is an agent published in the GitHub repository alphabravo-oss/guild (2 stars, last pushed 11d ago), licensed MIT. It adds 85 tokens to every session and 5,585 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other agents, from other repositories
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.
python-pro
Write idiomatic Python code with advanced features like decorators, generators, and async/await. Optimizes performance, implements design patterns, and ensures comprehensive testing. Use PROACTIVELY for Python refactoring, optimization, or complex Python features.
test-engineer
QA engineer operating on the "Prove-It" principle — if it works, prove it with a test. Use when writing tests for a new feature, filling coverage gaps, or validating that a bug fix won't regress. Can read, write and edit test files. Dispatch with Task tool for isolated test work.
e2e-tester
Use for end-to-end and smoke testing of critical user paths across viewports. Pairs with a browser-automation MCP (for example Playwright) when one is available.
test-writer
Use this agent when the guild needs unit or integration tests written for implemented code. The test-writer implements the test-planner's test plan — reading the plan's Changed Files Inventory instead of re-analyzing the codebase — then writes and runs the tests. Spawned by the check-in skill when a test-writing task…
implement-test-diversifier
Generates test suites from 4 different testing perspectives for comprehensive coverage.