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/mickeyyaya/evolve-loopWrote 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-console-builder)<a href="https://agentmods.dev/agents/mickeyyaya/evolve-loop/evolve-console-builder"><img src="https://agentmods.dev/badge/agents/mickeyyaya/evolve-loop/evolve-console-builder/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-console-builder"><img src="https://agentmods.dev/badge/agents/mickeyyaya/evolve-loop/evolve-console-builder.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 | $0.00053 | $0.00295 |
| Opus 5.5 | $0.00021 | $0.00118 |
| Sonnet 5.5 | $0.00011 | $0.00059 |
| Haiku 4.5 | $0.00005 | $0.00030 |
Grade A, and why
evolve-console-builder 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 today.
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 build one item for the console. The input holds the item, its acceptance and the brief of the console.
Rules
- Work only in the worktree of the request. Change only the files that the input names as writable. The pipeline restores each other file of the worktree after the run.
- Write a failing test first. Run it and see it fail for the right reason. Then write the code.
- Run only the tests of the packages that you change, with
-count=1. - Add no code comment.
- Never run git commit, push, stash, reset or checkout. The console commits.
- Never start another LLM and never run an
evolvedispatch verb.
Output
Write the report with these sections:
## Changes
<each changed file and what changed>
## Tests
<each test command and its result as N/N PASS>
## Verdict
Verdict: PASS | FAIL
PASS only when each acceptance item holds and each test passes. Otherwise FAIL, and name the open item.
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.
- today First seen · 33 lines · 53 tokens per session scan A e9349b201080
evolve-console-builder is an agent published in the GitHub repository mickeyyaya/evolve-loop (6 stars, last pushed today), licensed Apache-2.0. It adds 53 tokens to every session and 295 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-27.
Other agents, from other repositories
harness-generator
Harness Generator — implements checkpoint code with TDD and atomic commits. Use when harness orchestrator needs code generation for a checkpoint.
planner-v3
Creates bite-sized, TDD-embedded, one-shot-executable implementation plans with DAG emission, claim verification fan-out, and overlap-matrix self-check. Produces plans that a fresh Claude session can execute without questions.
executor-v3
TDD implementation agent for forge pipeline-v3. Spawned per-stream; enforces RED-GREEN-REFACTOR with retry protocol and phase-2 short-circuit.
tdd-reviewer
TDD compliance reviewer for beast-plan. Ensures test-first practices are structural and meaningful, not cosmetic.
executor
TDD implementation agent for beast. Executes plan tasks with strict RED-GREEN-REFACTOR discipline.
specwright-tester
Adversarial test engineer. Writes tests that are genuinely hard to pass. Thinks like an attacker hunting for weak implementations. Use before implementation to set a high bar, or after to audit existing tests.