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/captainme-ai/lead-dev-os/step1-write-specnpx skills add CaptainMe-AI/lead-dev-os --skill step1-write-specgit 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/step1-write-spec)<a href="https://agentmods.dev/skills/captainme-ai/lead-dev-os/step1-write-spec"><img src="https://agentmods.dev/badge/skills/captainme-ai/lead-dev-os/step1-write-spec.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 | $0.00020 | $0.01949 |
| Opus 5 | $0.00010 | $0.00975 |
| Sonnet 5 | $0.00004 | $0.00390 |
| Haiku 4.5 | $0.00002 | $0.00195 |
Grade A, and why
step1-write-spec 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 3d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Step 1: Write Spec
Interactively gather requirements for a new feature through structured Q&A, research, and visual analysis, then formalize into a structured specification document.
Instructions
You are a senior product engineer conducting a requirements discovery session and writing a formal specification. Your goal is to deeply understand what needs to be built and produce an implementable spec before any code is written. This skill writes documents only — implementation planning happens later, in /lead-dev-os:step3-implement-tasks.
Phase 1: Initialize
-
Ask the user: "What do you want to build?" — Accept a brief description (1-3 sentences is fine).
-
Create a dated spec folder with a visuals directory:
mkdir -p lead-dev-os/specs/YYYY-MM-DD-<spec-name>/planning/visualsUse kebab-case for
<spec-name>. -
Save the user's raw idea to
planning/initialization.md:# Initialization ## Raw Idea > [User's description verbatim] ## Date YYYY-MM-DD
Phase 2: Research Context
Before asking questions, silently research available project context to inform your questions:
-
Start by reading
agents-context/README.md— this is the index of all available concepts and standards. Use it to identify which files are relevant to the user's feature. Load only what you need, not everything. -
Based on the README, read only the relevant files:
agents-context/product/product-mission.md(if it exists) — understand the product's purpose and target usersagents-context/product/product-roadmap.md(if it exists) — see where this feature fits in the bigger picture- Any other concept files the README lists as relevant to this feature's domain
- Any standards files relevant to the feature's tech area
-
Concept-driven reusability scan — The concept files you read describe existing patterns, conventions, and architectural decisions — and they reference source file paths. Use these to identify reusable code without blindly searching the entire codebase. Note any relevant concepts and the source paths they reference.
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.
- 3d ago First seen · 153 lines · 20 tokens per session scan A 13ed04e6510c
step1-write-spec is a skill published in the GitHub repository CaptainMe-AI/lead-dev-os (2 stars, last pushed 14d ago), licensed MIT. It adds 20 tokens to every session and 1,949 once invoked, about $0.0001 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
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…
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…
conducting-deep-research
Use when asked for "deep research", "thorough analysis", "comprehensive report", "investigate", "due diligence", or when multiple sources are needed to answer complex questions. Produces well-sourced research reports through iterative refinement.
collecting-evidence
Use when researching a specific pillar and need to create traceable evidence objects. Guides creation of YAML evidence files with semantic IDs, confidence scores, and assumptions.
generating-constrained-specs
Use when generating PRD and architecture documents that must trace back to explicit decisions. Enforces citation requirements so no spec content exists without DEC- references.