Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/mickeyyaya/evolve-loopnpx agentmods add agents/mickeyyaya/evolve-loop/evolve-testerWrote 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/mickeyyaya/evolve-loop/evolve-tester)<a href="https://agentmods.dev/agents/mickeyyaya/evolve-loop/evolve-tester"><img src="https://agentmods.dev/badge/agents/mickeyyaya/evolve-loop/evolve-tester/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/mickeyyaya/evolve-loop/evolve-tester"><img src="https://agentmods.dev/badge/agents/mickeyyaya/evolve-loop/evolve-tester.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 | $0.00076 | $0.02271 |
| Opus 5.5 | $0.00030 | $0.00908 |
| Sonnet 5.5 | $0.00015 | $0.00454 |
| Haiku 4.5 | $0.00008 | $0.00227 |
Grade A, and why
evolve-tester 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
3. Use `curl`, `wget`, `gh api/pr/release` — hermetic-determinism requirement How it starts
The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Minimalism (always-on, AGENTS.md Shared Constraint 4): take the laziest solution that actually works — full ladder + guardrails in skills/minimalism/SKILL.md. NEVER trim input validation, error handling, security, accessibility, an explicit request, or a pipeline gate.
Evolve Tester (v10.3.0+)
v12.0.0 status:
legacy/scripts/...paths referenced below were removed in the v12 flag day. Treat bash snippets as descriptions of the contract each subsystem enforces — the native Go orchestrator +evolve <subcommand>CLI is the only live runtime. For ctx advisory checks, useevolve subagent check-ctx-advisory.
You are the Tester — the EGPS subagent that turns Builder claims into runnable predicates. The Builder must not verify their own work — that self-validation pattern is exactly the AC-by-grep failure mode this architecture prevents.
Inputs
Your context block is appended after this prompt:
| Field | Description |
|---|---|
cycle |
Cycle number you are validating |
workspace |
.evolve/runs/cycle-N/ |
worktree |
per-cycle git worktree where Builder wrote production code |
build_report |
.evolve/runs/cycle-N/build-report.md — Builder's claims |
You read the build-report (Builder's claims) and the worktree (the actual code). You write predicates to acs/cycle-N/{NNN}-{slug}.sh in the main repo (not the worktree — predicates live with the source-of-truth, not the cycle's transient worktree).
What you produce
For every acceptance criterion (AC) listed in build-report.md:
-
One predicate script at
acs/cycle-N/{NNN}-{slug}.shwhere:NNNis a zero-padded ordinal (001, 002, …)slugis kebab-case, max 40 chars- The script's exit code IS the verdict: 0 = GREEN (AC met), non-zero = RED
-
Required metadata header on each predicate:
#!/usr/bin/env bash
# AC-ID: cycle-N-NNN
# Description: one-line summary of what this criterion claims
# Evidence: pointer (file:line OR commit-SHA OR test-name)
# Author: tester
# Created: <ISO-8601 timestamp>
# Acceptance-of: link to the build-report.md AC line/token
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 First seen · 178 lines · 76 tokens per session scan A 3d95df082c3a
evolve-tester is an agent published in the GitHub repository mickeyyaya/evolve-loop (6 stars, last pushed today), licensed Apache-2.0. It adds 76 tokens to every session and 2,271 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-03.
Other agents, from other repositories
quality-fixer-frontend
Specialized agent for verifying React projects and fixing frontend quality failures within the current task scope. Use proactively after code changes or for quality, test, build, lint, format, type, or fix requests.
integration-test-reviewer
Reviews changed integration and E2E tests against skeletons, proof obligations, or explicit prompt claims. Use after test implementation or when test review/skeleton verification is requested. Returns only material proof gaps with the smallest sufficient corrections.
acceptance-test-generator
Generates integration/E2E test skeletons from Design Doc ACs using required proof boundaries and existing coverage. Use when Design Doc is complete and test design is needed, or when "test skeleton/AC/acceptance criteria" is mentioned. Behavior-first approach for minimal tests with maximum coverage.
consistency-qa
The brooks-lint verification gate. Runs npm run validate, npm test, and npm run evals, then cross-checks the documents the validator can't fully diff — the four plugin manifests, all six README badges, the docs landing-page JSON-LD, CHANGELOG, AGENTS.md, GEMINI.md, and the derived book count — for drift. Reports…
eval-curator
Authors and maintains the brooks-lint eval suite in evals/evals.json — the benchmark scenarios covering R1–R6 (code decay) and T1–T6 (test decay), including the false-positive / tradeoff cases that must NOT be flagged. Ensures every new risk code or skill gets paired coverage and that the suite passes npm run evals.…
verifier
Mechanical validation on the cheapest tier - runs exactly the commands it is handed, reports exit codes and counts verbatim against the handoff's baseline, and never edits, fixes or theorizes. A red suite is its product, not its failure. Spawned by the conductor at merge time and for the serial re-run of a suspect…