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.
npx skills add pktikkani/agent-skills --skill greenfieldgit clone --depth 1 https://github.com/pktikkani/agent-skillsWrote 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/skills/pktikkani/agent-skills/greenfield)<a href="https://agentmods.dev/skills/pktikkani/agent-skills/greenfield"><img src="https://agentmods.dev/badge/skills/pktikkani/agent-skills/greenfield/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/skills/pktikkani/agent-skills/greenfield"><img src="https://agentmods.dev/badge/skills/pktikkani/agent-skills/greenfield.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 | $0.00056 | $0.02329 |
| Opus 5 | $0.00028 | $0.01164 |
| Sonnet 5 | $0.00011 | $0.00466 |
| Haiku 4.5 | $0.00006 | $0.00233 |
Grade A, and why
greenfield 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.
How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Greenfield
Bootstrap a new repo with a discipline contract that a returning agent (or you, months later) can re-enter in one file-read instead of codebase archaeology. Generate the files below in the new repo's root (adapt content to the actual project — do not paste the examples verbatim). If a file already exists, update it; never clobber real content.
Core loop this skill enforces: PRODUCT.md is written before BLUEPRINT.md; every session, reread both before writing code; update STATUS.md as your last act before ending the session.
0. PRODUCT.md — the product contract (written FIRST)
The layer above architecture. Locks what success is before anything is designed, so that
evals, telemetry and the roadmap all trace to one outcome. Copy templates/PRODUCT.md from this
skill's bundle and fill it in with the human — never invent the outcome. Contains, in order:
- Outcome: the ONE number the customer will judge the product on, with today's value and the target (e.g. "commitments closed by due date: 40% → 70% in 90 days"). One outcome per product; more is a sign of no decision.
- User + opportunity tree (Teresa Torres): who the user is, and 3-5 opportunities (unmet needs / pains, in the user's words) that block the outcome. Solutions hang under opportunities; each solution lists the assumption that must hold for it to work.
- Failure modes: what would make the outcome fail even if the code is correct, ranked. For AI features these are things like "invented commitment", "wrong owner", "wrong date". These ARE the eval KPIs — /eval-discipline reads this list; one evaluator per row.
- Pre-ship evidence: for each failure mode, how it is measured before deploy (labelled dataset + evaluator name + threshold). No threshold → not shippable.
- Post-ship signals: for each failure mode, how it is observed in production (the event, the user action, the field). Same name as the eval column so a prod drop points to the eval to rerun. This is the telemetry spec — design it in, don't bolt it on.
- Discovery cadence: the weekly touchpoint with a real user (Torres: interview, not
survey) and where notes land (
docs/discovery/YYYY-MM-DD.md). - Traceability rule (verbatim): Every
## Roadmapline in BLUEPRINT.md names the opportunity or failure mode it serves. No line, no build.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago Changed · +29 lines 7adad4111e1c
- 9d ago First seen · 96 lines · 56 tokens per session scan A 81f3414a01db
greenfield is a skill published in the GitHub repository pktikkani/agent-skills (2 stars, last pushed 2d ago), licensed MIT. It adds 56 tokens to every session and 2,329 once invoked, about $0.0003 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…