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 lukedj78/dev-flow --skill prd-from-ideagit clone --depth 1 https://github.com/lukedj78/dev-flowWrote 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/lukedj78/dev-flow/prd-from-idea)<a href="https://agentmods.dev/skills/lukedj78/dev-flow/prd-from-idea"><img src="https://agentmods.dev/badge/skills/lukedj78/dev-flow/prd-from-idea/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/lukedj78/dev-flow/prd-from-idea"><img src="https://agentmods.dev/badge/skills/lukedj78/dev-flow/prd-from-idea.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 33 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium MCP Rug Pull · line 37 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 38 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 43 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00212 | $0.05918 |
| Opus 5.5 | $0.00085 | $0.02367 |
| Sonnet 5.5 | $0.00042 | $0.01184 |
| Haiku 4.5 | $0.00021 | $0.00592 |
Grade A, and why
prd-from-idea 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 — 336 lines — stays where its author put it; the contents beside it link to each section on GitHub.
prd-from-idea — idea → PROJECT.md + PRD.md
This skill turns an unstructured product idea into two artifacts that downstream skills depend on:
PROJECT.md— the strategic brief. One page. Audience, problem, value proposition, success criteria. The piece other humans read.PRD.md— the product requirements doc. Several pages. User stories, acceptance criteria, non-goals, open questions. The piece engineers and downstream skills consume.
The skill is interactive — it asks the user a small number of high-leverage questions and turns the answers into the docs. It does not invent PRD content from nothing. When nobody can answer (an autonomous run), it derives the answers from the brief and records them as assumptions instead — see Step 3 §Autonomous runs.
When this skill applies
- A user pastes a product idea ("I want to build a dashboard for X") and asks to start.
- Orchestrator (
dev-flow) routes here whenphaseisemptyoridea_captured. - A
PROJECT.mdexists butPRD.mddoesn't — the skill expands the brief into requirements.
If a PRD.md already exists, the skill enters revise mode: it reads the current PRD, asks what's wrong, and edits in place. It does not silently overwrite. A change that adds or removes a story is a scope change: it passes the scope check first (references/scope-check.md) and is recorded with scripts/scope.py record, one row in ## Scope changes. A PRD that predates ## Scope rules gets the section here (question 7b).
Contract
This skill follows the dev-flow contract — see references/contracts.md (vendored copy) for the canonical schema. Key facts:
- Output goes into
<project-root>/.workflow/. - Set
phase = "idea_captured"after writingPROJECT.md; setphase = "prd_drafted"after writingPRD.md. - Append a
historyentry tometa.jsonfor every run.
⚠️ Step 0 — the brief arrived as a file, not as a paste
The description above says "a user pastes a product idea", and often they don't: a real brief arrives
as .docx, .pptx, .pdf, .xlsx — an RFP, a client deck, a spec someone wrote in Word. Do not
ask the user to paste it, and do not summarise it from a partial read.
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 Changed · +50 lines 169088964d06
- 1mo ago Changed · +9 lines 23caffebf566
- 1mo ago Changed · +2 lines e304c2b86093
- 1mo ago First seen · 275 lines · 212 tokens per session scan A 9233c72c7b09
prd-from-idea is a skill published in the GitHub repository lukedj78/dev-flow (6 stars, last pushed 7d ago), licensed MIT. It adds 212 tokens to every session and 5,918 once invoked, about $0.0008 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 skills, from other repositories
sdlc-regulatory
AI-driven SDLC governance framework with quality gates, risk-based autonomy caps, change traceability, Definition of Done, and a compliance crosswalk (EU AI Act, NIST AI RMF, ISO/IEC 42001, SOC 2, GDPR). Use when running or reviewing work through the BMad-style subagent SDLC, enforcing gates, classifying risk, or…
agent-swarm
Agent skill for swarm - invoke with $agent-swarm.
moai-workflow-worktree
Git worktree management for parallel SPEC development with isolated workspaces, automatic branch registration, and seamless MoAI-ADK integration. Use when setting up parallel development environments.
moai-workflow-project
Integrated project management system covering documentation, language initialization, template optimization, docs generation, and JIT document loading. Absorbed from moai-workflow-templates, moai-docs-generation, and moai-workflow-jit-docs.
agentrq
Execute tasks assigned by humans or supervisor agents within a specific AgentRQ workspace. Use when you receive channel messages or need to report progress on tasks.
internal-comms
Author clear, high-impact internal engineering communications including 3P status updates, blameless incident postmortems, architecture decision memos, and leadership briefs. Use when writing technical updates, sprint reports, incident reviews, or organizational engineering announcements.