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 jimtin/production-ai --skill feature-design-preflightgit clone --depth 1 https://github.com/jimtin/production-aiWrote 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/jimtin/production-ai/feature-design-preflight)<a href="https://agentmods.dev/skills/jimtin/production-ai/feature-design-preflight"><img src="https://agentmods.dev/badge/skills/jimtin/production-ai/feature-design-preflight/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/jimtin/production-ai/feature-design-preflight"><img src="https://agentmods.dev/badge/skills/jimtin/production-ai/feature-design-preflight.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 | $0.00153 | $0.02169 |
| Opus 5 | $0.00077 | $0.01085 |
| Sonnet 5 | $0.00031 | $0.00434 |
| Haiku 4.5 | $0.00015 | $0.00217 |
Grade A, and why
feature-design-preflight 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 10d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feature Design Preflight
Purpose
Use this skill to prevent half-built features. Trace the requirement from user intent through the actual repo, platform, provider, library, data, failure modes, and tests before writing code.
The output is a short implementation readiness note with an explicit status: READY with concrete decisions, CONDITIONAL with safe defaults applied and assumptions listed, or BLOCKED with the exact clarifications or research needed.
Right-Sizing
This gate is for nontrivial features. When the request genuinely reuses a proven repo pattern end to end — one more field on an existing form, one more column in an existing report — say so, record that assumption in the completion report, and proceed without a readiness note. If the trace would surface a new provider, new failure mode, new schema, or new user-visible state, it is not trivial; run the preflight.
Operating Rules
- Be tool agnostic. Do not assume Vercel, S3, Cloudinary, Mux, Stripe, Clerk, Prisma, Playwright, a PDF library, or any other provider is the right answer until the repo and requirement prove it.
- Discover the repo's current stack, provider choices, constraints, and conventions before selecting architecture.
- Check authoritative current docs when provider limits, library capabilities, SDK versions, file-size limits, timeouts, pricing-sensitive behavior, or API contracts affect the design. Record each load-bearing limit or capability in the readiness note with the concrete value, the source, and the date checked. "Docs checked" without the value is not evidence.
- Prefer boring, proven architecture over clever shortcuts. Reject naive implementations that are likely to fail at realistic scale or in production.
- Stop and ask when a requirement cannot be safely inferred, when tradeoffs need product approval, or when the implementation path materially changes cost, UX, security, data retention, or operational burden.
- Leave a traceable decision record before implementation begins. For substantial features, write the readiness note to a file (for example
docs/plans/<feature>-readiness.md, or append it to the planning file when invoked from$clarify-before-build) so the record survives the session and is reviewable in git. In plan modes that prohibit file writes, keep the note in-message and restate it after any context loss.
What ships with it
4 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.
- 10d ago First seen · 126 lines · 153 tokens per session scan A f7a98bea96ec
feature-design-preflight is a skill published in the GitHub repository jimtin/production-ai (1 stars, last pushed 2mo ago), licensed MIT. It adds 153 tokens to every session and 2,169 once invoked, about $0.0008 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
git-workflow
This skill should be used when the user asks to "create git commit", "manage branches", "follow git workflow", "use Conventional Commits", "handle merge conflicts", or asks about git branching strategies, version control best practices, pull request workflows. Provides comprehensive Git workflow guidance for team…
daily-paper-generator
Use when the user asks to generate daily paper digests on a general topic. This skill supports both arXiv and bioRxiv (or either one), then produces structured Chinese/English summaries for selected papers.
codex-autoresearch
Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding…
clipboard
Copy text to clipboard with optional rich formatting. Triggers on "copy to clipboard", "copy that", "pbcopy", "copy formatted", "copy rich text".
neo4j-modeling-skill
Design, review, and refactor Neo4j graph data models. Use when choosing node labels vs relationship types vs properties, migrating relational/document schemas to graph, detecting anti-patterns (generic labels, supernodes, missing constraints), designing intermediate nodes for n-ary relationships, enforcing schema with…
agent-safety
Use when bounding an LLM agent that already runs — scoping its task domain, gating tools to least privilege, defending against prompt injection in untrusted web/email/RAG text, requiring human approval on irreversible actions, capping runtime and cost, or triaging what it already did. NOT building the loop, tools, or…