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 clarify-before-buildgit 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/clarify-before-build)<a href="https://agentmods.dev/skills/jimtin/production-ai/clarify-before-build"><img src="https://agentmods.dev/badge/skills/jimtin/production-ai/clarify-before-build/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/clarify-before-build"><img src="https://agentmods.dev/badge/skills/jimtin/production-ai/clarify-before-build.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 | $0.00107 | $0.02108 |
| Opus 5 | $0.00053 | $0.01054 |
| Sonnet 5 | $0.00021 | $0.00422 |
| Haiku 4.5 | $0.00011 | $0.00211 |
Grade A, and why
clarify-before-build 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 9d 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clarify Before Build
Core Rule
Do not start implementation while material planning ambiguity remains. Keep questioning until the plan is specific enough that another capable engineer could execute it without guessing.
This skill is not for producing a quick plan and moving on. It is a planning gate: ask, refine, challenge, restate, and only then produce an implementation-ready plan.
Right-Sizing the Gate
Match the gate's weight to the scope's risk, not to the request's phrasing.
Run the full gate (planning ledger, question rounds, Shared Understanding Contract) when any of these hold:
- multiple repos, services, schemas, or delivery slices
- schema/migration, auth/permission, payment, upload/parsing, background-job, or deployment changes
- multiple roles, tenants, or substantial user-facing workflows
- provider, library, or architecture selection with meaningful tradeoffs
- the user asked for a plan, roadmap, design, or architecture document
Run a lightweight pass when the scope is one repo, a few files, and none of the full-gate triggers apply:
- Summarize the understanding in 2-3 bullets.
- State assumptions inline and ask only blocking questions (0-2).
- Proceed, and record the stated assumptions in the completion report instead of a contract.
If a lightweight pass uncovers a full-gate trigger, escalate to the full gate and say so. Never use the lightweight pass to dodge the contract on substantial work.
Operating Mode
- State that planning mode is active.
- Summarize the current understanding in 3-6 bullets.
- Identify unknowns, assumptions, contradictions, risks, and decisions.
- Ask the next most important questions in a focused batch.
- Wait for answers before finalizing the plan.
- Repeat until no material ambiguity remains.
- Produce a Shared Understanding Contract and ask for explicit confirmation.
- Only after confirmation, offer implementation sequencing — and for substantial user-facing work, name
$user-action-coverage-reviewas the first post-confirmation step.
What ships with it
3 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.
- 9d ago First seen · 165 lines · 107 tokens per session scan A caeee86acbe5
clarify-before-build is a skill published in the GitHub repository jimtin/production-ai (1 stars, last pushed 2mo ago), licensed MIT. It adds 107 tokens to every session and 2,108 once invoked, about $0.0005 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…
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…
clipboard
Copy text to clipboard with optional rich formatting. Triggers on "copy to clipboard", "copy that", "pbcopy", "copy formatted", "copy rich text".
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…