What is evolve-builder-reference?

A reference guide for an Evolve build process, with extra instructions loaded only when certain conditions apply. Evolve is a staged workflow for planning, building, checking, and shipping code.

Use it when the task involves relevant routes, pages, components, forms, authentication flows, end-to-end grading, or a specifically requested end-to-end testing skill.

It keeps the normal build instructions smaller while providing detailed guidance for tasks that need special handling, such as end-to-end tests.

evolve-builder-reference — Agent by mickeyyaya

Install

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.

agentmods

npx agentmods add agents/mickeyyaya/evolve-loop/evolve-builder-reference

Clone the repo

git clone --depth 1 https://github.com/mickeyyaya/evolve-loop

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 4,100 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00000	$0.04100
Opus 5	$0.00000	$0.02050
Sonnet 5	$0.00000	$0.00820
Haiku 4.5	$0.00000	$0.00410

Measured yesterday against content hash ea149b532462, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

evolve-builder-reference 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 yesterday.

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.

Banned: `grep -q` as only check, `exit 0` no-op, `curl`, `sleep` > 2s.

agents/evolve-builder-reference.md · 416 lines

How it starts

The opening of the file, as written. The whole thing — 416 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Builder Reference (Layer 3 — on-demand)

Sections here are loaded only when specific build conditions activate. In the common build path, none of this is needed. v8.64.0 Campaign D Cycle D2 split.

The builder's compact role-card (Layer 1) lives at agents/evolve-builder.md and includes a ## Reference Index pointing here.

Section: e2e-test-generation

Loaded when ANY of the following is true:

task.recommendedSkills contains everything-claude-code:e2e-testing or ecc:e2e
The eval definition at .evolve/evals/<task-slug>.md contains an ## E2E Graders section
task.filesToModify touches routes, pages, components, forms, or auth flows

Otherwise: skip this section entirely. Do not invoke the e2e-testing skill speculatively.

Workflow:

Invoke the everything-claude-code:e2e-testing skill (or the closest available e2e alternative found in the skill inventory) via your native skill invocation tool. Pass a user-flow description derived from the task's acceptance criteria (e.g., "verify /health page renders with status text and correct HTTP 200").
The skill generates tests/e2e/<task-slug>.spec.ts using the Page Object Model pattern.
Run the generated test inside the worktree: npx playwright test tests/e2e/<task-slug>.spec.ts --reporter=list,html.
If the test fails due to an implementation gap, iterate on the implementation — not the test — until it passes. Weakening or skipping the generated test is eval tampering (Auditor D.5 flags CRITICAL).
Commit the generated test file(s) as part of the task's worktree commit.
Record the test path and pass result in build-report.md under a new ## E2E Verification section (see Output template in Layer 1).

Platform fallback: If npx playwright is unavailable in this project, the skill's own setup flow should run npx playwright install --with-deps. If installation fails, emit a single ## E2E Verification row with status: SKIPPED — reason: playwright not available rather than halting the build.

Read the full file on GitHub · 416 lines

Changes

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.

yesterday First seen · 416 lines · 0 tokens per session scan A ea149b532462

Subscribe to this mod's changes

evolve-builder-reference is an agent published in the GitHub repository mickeyyaya/evolve-loop (5 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 4,100 tokens. 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.

Code review Planning Testing ai-agents ai-pipeline autonomous-coding claude-code claude-code-plugin code-quality

evolve-builder-reference

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Makes network callslowCapability

How it starts

Builder Reference (Layer 3 — on-demand)

Section: e2e-test-generation

What this file has done since we first saw it

Other agents, from other repositories

github-action-reviewer

godmode-builder

lead

replanner

Music Producer

geo-schema-render