sf-builder

An execution agent for software tasks that checks how code is used before changing it, follows the repository's existing patterns, and builds and verifies each task.

In plain words
What is it for?
Use it to implement planned changes, inspect consumers of affected code, run builds or type checks, fix build failures, and verify each task's result.
Why use it?
It reduces the risk that a change breaks other files or leaves the project unable to build by requiring consumer checks and immediate verification.

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/shipfast-ai/shipfast/builder
Clone the repo
git clone --depth 1 https://github.com/shipfast-ai/shipfast
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,205 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 $0.00023 $0.02205
Opus 5 $0.00012 $0.01103
Sonnet 5 $0.00005 $0.00441
Haiku 4.5 $0.00002 $0.00220

Measured 2d ago against content hash 4c1e38ac651c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sf-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 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/builder.md · 223 lines

How it starts

The opening of the file, as written. The whole thing — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md precedence: If the project has a CLAUDE.md file, its directives override plan instructions. Read it first if it exists.

<before_any_change>

RULE ZERO: Impact Analysis Before Every Modification

Before deleting, removing, renaming, or modifying ANY function, type, selector, export, or component:

  1. grep -r "<name-being-changed>" --include="*.ts" --include="*.tsx" --include="*.js" --include="*.jsx" .
  2. Count results. If OTHER files use it → update those files too, or keep the original
  3. NEVER remove without checking. This is the #1 cause of cascading breaks.

If the task plan lists consumers, verify the list is current before proceeding. </before_any_change>

<execution_order>

Strict Per-Task Sequence

For EACH task (not at the end — PER TASK):

Step 1: READ — Read every file you will modify. Read the plan's consumer list. Step 2: GREP — Verify consumers of anything you'll change/remove Step 3: IMPLEMENT — Make changes following existing patterns Step 4: BUILD — Run npm run build / tsc --noEmit / cargo check IMMEDIATELY Step 5: FIX — If build fails, fix (up to 3 attempts per task) Step 6: VERIFY — Run the task's verify command from the plan Step 7: COMMIT — Stage specific files only, conventional format

Do NOT skip Steps 2, 4, or 6. Do NOT batch multiple tasks before building. Do NOT commit until build passes. </execution_order>

<deviation_tiers>

Auto-fix (no approval needed)

Tier 1 — Bugs: Logic errors, null crashes, race conditions, security holes → Fix inline Tier 2 — Critical gaps: Missing error handling, validation, auth checks → Add inline Tier 3 — Blockers: Missing imports, type errors, broken deps → Fix inline

Track every deviation: [Tier N] Fixed: [what] in [file]

STOP and report

Tier 4 — Architecture: New DB tables, schema changes, library swaps, breaking APIs → STOP. Report: "This requires [change]. Proceed?"

Read the full file on GitHub · 223 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 · 223 lines · 23 tokens per session scan A 4c1e38ac651c

Subscribe to this mod's changes

sf-builder is an agent published in the GitHub repository shipfast-ai/shipfast (4 stars, last pushed 4mo ago), licensed MIT. It adds 23 tokens to every session and 2,205 once invoked, about $0.0001 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.

Related

Other agents, from other repositories

quinn

Quinn Torres, UI/UX Designer -- specialist prompt template. Loaded by the directive pipeline when the COO casts this specialist for design review or UI planning.

andrew-yangy/gru-ai · 35 tokens

devon

Devon Lee, Full-Stack Engineer -- specialist prompt template. Loaded by the directive pipeline when the COO casts this specialist for a task's build phase. Handles work that spans frontend and backend, or scope too broad for a single-domain specialist.

andrew-yangy/gru-ai · 54 tokens

morgan

Morgan Park, COO -- the orchestrator. Invoke Morgan for project planning, task decomposition, team casting decisions, token budget management, and operational coordination. Use when starting new projects, breaking down goals into tasks, deciding which agents to involve, or when a project needs structure. Use…

andrew-yangy/gru-ai · 68 tokens

priya

Priya Sharma, CMO — the growth driver. Invoke Priya for marketing strategy, SEO decisions, content strategy, competitive positioning, growth experiments, landing page copy, and go-to-market planning. Use when deciding how to reach users, improve visibility, craft messaging, or analyze what competitors are doing in the…

andrew-yangy/gru-ai · 67 tokens

sam

Sam Park, QA Engineer -- specialist prompt template. Loaded by the directive pipeline when the COO casts this specialist for a task's build phase, review phase, or as the Investigator in the two-agent audit flow (Step 3b Phase 1).

andrew-yangy/gru-ai · 53 tokens

sarah

Sarah Chen, CTO — the architect. Invoke Sarah for architecture decisions, technical design reviews, code quality assessments, technology choices, pre-mortems on technical risk, and setting engineering standards. Use when evaluating trade-offs between approaches, reviewing PRs for architectural concerns, or when a…

andrew-yangy/gru-ai · 66 tokens