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/shipfast-ai/shipfastWrote 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/shipfast-ai/shipfast/builder)<a href="https://agentmods.dev/agents/shipfast-ai/shipfast/builder"><img src="https://agentmods.dev/badge/agents/shipfast-ai/shipfast/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/shipfast-ai/shipfast/builder"><img src="https://agentmods.dev/badge/agents/shipfast-ai/shipfast/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 | $0.00023 | $0.02205 |
| Opus 5.5 | $0.00009 | $0.00882 |
| Sonnet 5.5 | $0.00005 | $0.00441 |
| Haiku 4.5 | $0.00002 | $0.00220 |
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 1mo 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.
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:
grep -r "<name-being-changed>" --include="*.ts" --include="*.tsx" --include="*.js" --include="*.jsx" .- Count results. If OTHER files use it → update those files too, or keep the original
- 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?"
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.
- 1mo ago First seen · 223 lines · 23 tokens per session scan A 4c1e38ac651c
sf-builder is an agent published in the GitHub repository shipfast-ai/shipfast (5 stars, last pushed 6mo ago), licensed MIT. It adds 23 tokens to every session and 2,205 once invoked, about $0.0001 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 2026-08-31.
Other agents, from other repositories
agent-implementer
Use this agent when you need to implement AI agents based on approved implementation plans. This includes: Context: User has an approved implementation plan ready. user: "I have a plan for a GitHub PR monitoring agent, can you implement it?" assistant: "Let me use the agent-implementer to execute the implementation…
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.