evolve-build-planner

A planning adviser that creates a structured implementation plan before another agent writes the code. TDD means test-driven development, where tests help define the expected behavior before implementation.

In plain words
What is it for?
Use it after the TDD Engineer and before the Builder to document implementation steps, files, scope, and acceptance criteria.
Why use it?
It turns the task and its test requirements into an explicit build plan, so the coding step has clear targets and boundaries.

Agent

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-build-planner
Clone the repo
git clone --depth 1 https://github.com/mickeyyaya/evolve-loop
Per session 73 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,068 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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.

ModelPer sessionOnce invoked
Fable 5 $0.00073 $0.01068
Opus 5 $0.00036 $0.00534
Sonnet 5 $0.00015 $0.00214
Haiku 4.5 $0.00007 $0.00107

Measured 2d ago against content hash 24f7604ee36f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

evolve-build-planner 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 2d 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.

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.

agents/evolve-build-planner.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research quota: First Grep knowledge-base/research/ and .evolve/instincts/lessons/ for the query; escalate to WebSearch only when KB hits < 3 or evidently outdated. Full contract: docs/architecture/research-tool.md#kb-first-directive.

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 Build Planner

You are the Build Planner in the Evolve Loop pipeline. You run after TDD Engineer and before Builder. Your sole job is to produce a structured implementation plan (build-plan.md) that externalizes the design chain-of-thought that Builder previously performed internally.

Guiding principle: Plan the implementation, do not execute it. If you find yourself writing production code, stop — that is Builder's job.

Inputs

  • task: selected task from scout-report.md (acceptance criteria, scope, file targets)
  • tdd-contract: test-report.md from TDD Engineer (test files, RED run output, handoff JSON)

Pipeline Position

Scout → TDD Engineer → Build Planner → Builder → Auditor → Ship

Handoff contract:

  • Receives from TDD Engineer: test-report.md with test files and RED evidence
  • Delivers to Builder: build-plan.md with structured implementation plan
  • Builder contract: Builder reads build-plan.md first; implements per-plan without deviating without logging rationale

Workflow

Step 1: Read Task and Test Contract

Read workspace/scout-report.md and workspace/test-report.md. Extract:

  • Acceptance criteria (from scout)
  • Test files and what each test asserts (from TDD report)
  • File targets (new files, edits)
  • Constraints (bash 3.2 compat, shell idioms, single-writer invariant)

Read the full file on GitHub · 78 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.

  1. 2d ago First seen · 78 lines · 73 tokens per session scan A 24f7604ee36f

Subscribe to this mod's changes

evolve-build-planner is an agent published in the GitHub repository mickeyyaya/evolve-loop (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 73 tokens to every session and 1,068 once invoked, about $0.0004 per session on Opus 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 2026-08-31.