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/define-standardsnpx skills add CaptainMe-AI/lead-dev-os --skill define-standardsgit 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/define-standards)<a href="https://agentmods.dev/skills/captainme-ai/lead-dev-os/define-standards"><img src="https://agentmods.dev/badge/skills/captainme-ai/lead-dev-os/define-standards.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 | $0.00019 | $0.00655 |
| Opus 5 | $0.00010 | $0.00328 |
| Sonnet 5 | $0.00004 | $0.00131 |
| Haiku 4.5 | $0.00002 | $0.00065 |
Grade A, and why
define-standards 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 4d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Define Standards
Establish coding style, conventions, architecture patterns, and quality standards for the project.
Instructions
You are a senior engineering lead. Help the user define project standards that will guide all future development.
Phase 1: Discovery
Read agents-context/README.md first — use this index to understand what concepts and standards already exist. Then read only the relevant files to avoid duplicating or contradicting established standards.
Read agents-context/product/product-mission.md if it exists to understand the technology stack.
Read agents-context/standards/ to see which standards already exist. Ask the user about their technology stack to understand which standards are relevant.
Ask the user the following questions:
Coding Style:
- Do you follow an existing style guide? (e.g., Airbnb JS, StandardRB, PEP 8, Google style guides)
- What are your naming conventions? (camelCase vs snake_case for variables, files, components, etc.)
- What formatter/linter do you use or want to use?
Architecture: 4. What architectural pattern does the project follow? (MVC, microservices, modular monolith, etc.) 5. How do you organize files? (By feature, by type, domain-driven?) 6. What patterns do you use for error handling? (Result types, exceptions, error boundaries?)
Testing: 7. What testing framework do you use? 8. What is your testing philosophy? (TDD, test-after, coverage targets?) 9. What should always be tested vs. what's optional?
Quality & Process: 10. What does your PR/review process look like? 11. Any specific security or performance standards?
Phase 2: Generate Standards
Based on responses, create standards files in agents-context/standards/:
- Universal standards (coding style, architecture) →
agents-context/standards/ - Stack-specific standards →
agents-context/standards/(e.g.,python-conventions.md,fastapi-patterns.md)
agents-context/standards/coding-style.md — Naming, formatting, file organization, language-specific conventions.
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.
- 4d ago First seen · 67 lines · 19 tokens per session scan A 40c00db8a955
define-standards is a skill published in the GitHub repository CaptainMe-AI/lead-dev-os (2 stars, last pushed 15d ago), licensed MIT. It adds 19 tokens to every session and 655 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…
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…
holdout-validation
Cross-reference agent self-review claims against actual file state using hidden holdout scenarios, producing mapped P1/P2/P3 findings that reference visible acceptance criteria only. Use when verifying implementation completeness after self-review in start (Phase 4 VERIFY), address (convergence check), or review…
runtime-verification
Verify code works at runtime through build verification (mandatory), LSP diagnostics, ad-hoc verification for projects without frameworks, E2E and smoke tests, and visual verification (screenshot-analyze-verify for UI changes). Skip whitelist strictly enforced (markdown-only, config-only, dependency-bump-only with…