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 agentmods add skills/evgenii-studitskikh/claude-code-saas-studio/write-prdnpx skills add evgenii-studitskikh/Claude-Code-SaaS-Studio --skill write-prdgit clone --depth 1 https://github.com/evgenii-studitskikh/Claude-Code-SaaS-StudioWrote 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/evgenii-studitskikh/claude-code-saas-studio/write-prd)<a href="https://agentmods.dev/skills/evgenii-studitskikh/claude-code-saas-studio/write-prd"><img src="https://agentmods.dev/badge/skills/evgenii-studitskikh/claude-code-saas-studio/write-prd.svg" alt="Measured on agentmods" 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 | $0.00044 | $0.00499 |
| Opus 5 | $0.00022 | $0.00249 |
| Sonnet 5 | $0.00009 | $0.00100 |
| Haiku 4.5 | $0.00004 | $0.00050 |
Grade A, and why
write-prd 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 5d 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.
What it actually says
Transform the idea-validation canvas into a structured Product Requirements Document that the engineering team can act on. Non-autonomous: every section is presented for approval before the file is written; review intensity controls how much detail is required before proceeding.
Phases
- Load context — read
docs/specs/idea-validation.md. If it is missing or contains a PIVOT/KILL verdict, stop and direct the user to/validate-ideafirst. Summarize the validated bet in two sentences and confirm it is still accurate. - Elicit goals and users — work through the PRD skeleton from
.claude/templates/prd.md: confirm the primary goal, secondary goals, and the one or two target user personas. Ask one question at a time; do not over-interview. - Draft user stories — propose a ranked list of user stories in "As a [persona], I want [action] so that [outcome]" format, each with two or three acceptance criteria. Present the list; let the user add, remove, or reprioritize before proceeding.
- Define non-goals and success metrics — propose explicit non-goals (what will NOT be built in v1) and two to four measurable success metrics tied to the goals. Get the user's sign-off on this list — it becomes the scope boundary for
/scope-check. - Write the draft — fill
.claude/templates/prd.mdwith everything gathered and write the draft todocs/specs/prd.md. Show the draft inline before writing; underfullreview, walk through each section; underleanorsolo, write directly after a single confirmation. - Next step — on approval, point to
/map-flowsto derive the screen and journey list.
Output
docs/specs/prd.md — a complete PRD. Writes nothing else without approval.
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.
- 5d ago First seen · 23 lines · 44 tokens per session scan A 506a001ee18e
write-prd is a skill published in the GitHub repository evgenii-studitskikh/Claude-Code-SaaS-Studio (1 stars, last pushed 2mo ago), licensed MIT. It adds 44 tokens to every session and 499 once invoked, about $0.0002 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
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
create-modal
Create declarative modals using the modal library API. Covers modal types (confirm, input, select, form), sections (Text, Buttons, Input, Textarea, Checkbox, List, Combo, When, Custom), rendering with OverlayModal, and keyboard/mouse handling. Use when adding modals or dialogs to the application.
ap-juror
L4 terminal leaf - G7 SIGN-OFF. One independent sign-off panel seat that saw none of the intermediate work. Binary PASS/FAIL on opened evidence; default-FAIL. A FAIL naming a P0/P1 blocker is NOT arbitrable into PASS.
openlore-brainstorm
Transform a feature idea into an annotated story using a Domain Sketch or Constrained Option Tree. Use when asked to brainstorm, explore, or shape a feature before implementation.
gemigo-cli
Use when the user wants to publish an already-built static website or front-end app through GemiGo, such as a Vite/React/Vue static build, plain HTML/CSS/JS page, landing page, demo, docs site, or small browser app, and get a hosted public URL.
nextclaw-dead-code-governance
当用户要求扫描、识别、清理、常态化治理 NextClaw 仓库里的死代码、无用代码、unused files、unused exports、unused dependencies，尤其是核心包越来越臃肿、想删旧实现或做定期减债时使用。.