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 CaptainMe-AI/lead-dev-os --skill plan-productgit clone --depth 1 https://github.com/CaptainMe-AI/lead-dev-osWrote 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/captainme-ai/lead-dev-os/plan-product)<a href="https://agentmods.dev/skills/captainme-ai/lead-dev-os/plan-product"><img src="https://agentmods.dev/badge/skills/captainme-ai/lead-dev-os/plan-product/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/captainme-ai/lead-dev-os/plan-product"><img src="https://agentmods.dev/badge/skills/captainme-ai/lead-dev-os/plan-product.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 | $0.00016 | $0.00501 |
| Opus 5.5 | $0.00006 | $0.00200 |
| Sonnet 5.5 | $0.00003 | $0.00100 |
| Haiku 4.5 | $0.00002 | $0.00050 |
Grade A, and why
plan-product 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 1mo 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Product
Define the product mission, vision, target users, and technology stack for this project.
Instructions
You are a strategic product advisor. Guide the user through defining their product foundation.
Phase 1: Discovery
Ask the user the following questions one group at a time, waiting for responses before continuing:
Group A — Mission & Vision:
- What problem does this product solve? Who feels this pain most acutely?
- What is your one-sentence mission statement? (If unsure, we'll draft one together.)
- What does success look like in 6 months? In 2 years?
Group B — Users & Market: 4. Who are your primary users? Describe 1-2 personas. 5. Are there existing solutions? What makes yours different? 6. What is the minimum feature set for a first release?
Group C — Technical Foundation: 7. What technology stack are you using or considering? (Languages, frameworks, databases, infrastructure) 8. Are there any technical constraints? (Legacy systems, compliance requirements, team expertise) 9. What is your deployment target? (Cloud provider, self-hosted, edge, etc.)
Phase 2: Synthesis
After gathering responses, generate a product mission document using the template in template.md. For a filled-in example, see examples/saas-project-tracker.md.
Phase 3: Output
Save the document to agents-context/product/product-mission.md.
Phase 4: Update README
Read agents-context/README.md. Under the ## Product section, ensure there is an uncommented entry for product-mission.md. If the entry is inside an HTML comment block, uncomment it. If no entry exists, add one:
- **[product-mission.md](product/product-mission.md)** — Product mission, vision, target users, and technology stack
Phase 5: Summary
Tell the user:
- "Product mission saved to
agents-context/product/product-mission.md" - "Updated
agents-context/README.mdindex" - Suggest running
/lead-dev-os:plan-roadmapnext to create a feature roadmap based on this mission.
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.
- 1mo ago First seen · 57 lines · 16 tokens per session scan A 00199f23fdf9
plan-product is a skill published in the GitHub repository CaptainMe-AI/lead-dev-os (2 stars, last pushed 2mo ago), licensed MIT. It adds 16 tokens to every session and 501 once invoked, about $0.0001 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
evolution-auditor
Run a structured organizational design health check — operationalizing the governance learning loop and decision ledger by collecting operational evidence, measuring gate effectiveness, detecting genome drift, and producing an evolution audit with routed recommendations saved to $HOME/.ai-first-kit/. Maintains the…
nci-manipulation-analysis
Use when asked to analyze content for manipulation, propaganda, disinformation patterns, or when user provides a URL or text asking "is this manipulative?", "analyze this for bias", "check for propaganda", or similar requests. Detects emotional manipulation, suspicious timing, uniform messaging, tribal division, and…
evidence-ledger
Record every material claim as a row in 00-control/evidence-ledger.md carrying a source-authority level and a claim state (verified, corroborated, reported, inferred, unknown, not applicable), and keep observed, interpreted, unknown, and recommended content in visibly separate blocks. Use when inventorying sources…
decision-journal
Extracts and structures development decisions from diffs, manages decision journal entries, and detects human gate triggers. Use when logging decisions during gh-start, gh-commit, or gh-address. Use when summarizing decisions for PR bodies or when checking for gate-triggering changes like new dependencies, security…
ai-first-kit
Navigate organizational redesign for AI with a structured 13-skill toolkit that produces persistent artifacts in $HOME/.ai-first-kit/. Routes founders and leaders to the right specialist skill — coordination audit, organizational genome, specification writing, quality gates, governance, role design, political…
coordination-audit
Produce a structured organizational diagnostic that quantifies time spent on specification vs coordination vs execution, saved as a persistent audit artifact to $HOME/.ai-first-kit/. Conducts a guided 5-question interview, classifies every workflow structure by actual function, and identifies highest-ROI automation…