builder-guidance

builder-guidance is an agent for coding agents from Hulupeep/Specflow. It costs 0 tokens per session (918 once invoked), scanned A, original, MIT.

Decision guidance for coding agents that build or change software during active implementation work.

In plain words
What is it for?
It helps choose how to handle test-environment failures, dependency stubs, migrations, frontend work, and edge-function work.
Why use it?
It helps avoid quick fixes that create harder problems later, especially when a failing test is caused by the test setup rather than the product code.

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/hulupeep/specflow/builder-guidance
Clone the repo
git clone --depth 1 https://github.com/Hulupeep/Specflow

Wrote 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.

agentmods badge for builder-guidance

README.md
[![agentmods](https://agentmods.dev/badge/agents/hulupeep/specflow/builder-guidance.svg)](https://agentmods.dev/agents/hulupeep/specflow/builder-guidance)
Your own site
<a href="https://agentmods.dev/agents/hulupeep/specflow/builder-guidance"><img src="https://agentmods.dev/badge/agents/hulupeep/specflow/builder-guidance.svg" alt="Measured on agentmods" height="20"></a>
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 918 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 $0.00000 $0.00918
Opus 5 $0.00000 $0.00459
Sonnet 5 $0.00000 $0.00184
Haiku 4.5 $0.00000 $0.00092

Measured 5d ago against content hash 017b437d6c26, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

builder-guidance 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 5d 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/builder-guidance.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.

Builder Guidance

Decision frameworks for builder-style agents (sprint-executor, migration-builder, frontend-builder, edge-function-builder, etc.) during active implementation work.

These aren't rules that can be mechanically enforced. They're defaults the builder should reach for when a specific trigger fires. The goal is to prevent reflex decisions from becoming entangling patches.


Harness-Issue Triage

Trigger: a test you just wrote (or modified) fails for harness reasons — ESM import crashes, missing module transforms, fake logger shapes, module resolution errors, etc. The product code is fine; the test environment is the problem.

The default LLM reflex is to stub. Stubbing is the cheapest local fix. It is also the most entangling choice, because every future test in this area will need the same stub, and the stubs hide real import coupling that the runtime path doesn't hide.

Before reaching for jest.mock() or vi.mock(), consider the options:

Option A — Stub the dependency at the test boundary

The reflex. Cheapest upfront, most entangling long-term.

  • Fast: add jest.mock('pino-http', ...) and move on
  • Cost: every future test that imports the same dependency needs the same stub
  • Cost: the stub hides real coupling from the test surface
  • Use when: the dependency is trivially fake-able (a logger, a telemetry sender) and you can document the stub pattern for future tests to reuse

Option B — Use an existing factory/helper that avoids the problematic import

If the workspace already has a createApp(), buildServer(), or similar, use it.

  • The factory was probably created to isolate problematic imports in the first place
  • Free: no new code
  • Use when: a factory exists. Search the workspace before stubbing.

Option C — Refactor the product code to make it test-friendly

Introduce an app-factory, extract a handler, or move the transitive-import source behind an interface.

  • Slower upfront: requires changing product code, not just test code
  • Correct long-term: the test surface and the runtime surface stay aligned
  • Use when: multiple tests will hit the same import problem, or when stubbing would hide an important coupling

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. 5d ago First seen · 78 lines · 0 tokens per session scan A 017b437d6c26

Subscribe to this mod's changes

builder-guidance is an agent published in the GitHub repository Hulupeep/Specflow (24 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 918 tokens. 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 2026-08-30.

Related

Other agents, from other repositories

api-architect

Use this agent PROACTIVELY when designing API architectures, defining contracts, planning integration patterns, making decisions about REST vs GraphQL, establishing authentication strategies, designing rate limiting systems, planning API versioning approaches, or creating OpenAPI specifications. Invoke for any API…

lando-labs/cami · 66 tokens

code-reviewer

Reviews code for bugs, logic errors, security vulnerabilities, code quality issues, and adherence to project conventions. Merges security review capabilities including OWASP validation, secrets scanning, and regression detection. Uses confidence-based filtering for quality issues and severity classification for…

zircote-plugins/refactor · 65 tokens

architect

Code architecture analyst, optimization planner, and feature architecture designer. Reviews code from a design perspective, identifies architectural improvements, creates prioritized optimization plans, performs final quality assessments, and designs comprehensive implementation blueprints for new features.

zircote-plugins/refactor · 45 tokens

refactor-code

Code implementation specialist for refactoring workflows. Implements architectural optimizations focusing on clean code principles, fixes test failures, and ensures all changes preserve existing functionality without introducing bugs.

zircote-plugins/refactor · 37 tokens

code-explorer

Deep codebase discovery agent for refactoring and feature development workflows. Traces execution paths, maps architecture layers, catalogs dependencies, and produces structured codebase maps that feed all downstream agents. Runs as Phase 0.5 in refactoring or as parallel explorers in feature development.

zircote-plugins/refactor · 59 tokens

feature-code

Implementation specialist for new feature development. Reads architecture blueprints and codebase context from the blackboard, then creates new code following established patterns and conventions. Designed for feature-dev workflows.

zircote-plugins/refactor · 39 tokens