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/create-or-update-conceptsnpx skills add CaptainMe-AI/lead-dev-os --skill create-or-update-conceptsgit 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/create-or-update-concepts)<a href="https://agentmods.dev/skills/captainme-ai/lead-dev-os/create-or-update-concepts"><img src="https://agentmods.dev/badge/skills/captainme-ai/lead-dev-os/create-or-update-concepts.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 | $0.00046 | $0.04986 |
| Opus 5 | $0.00023 | $0.02493 |
| Sonnet 5 | $0.00009 | $0.00997 |
| Haiku 4.5 | $0.00005 | $0.00499 |
Grade A, and why
create-or-update-concepts 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 6d 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 — 347 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create or Update Concepts
Scan and analyze the project codebase to populate agents-context/concepts/ with concept files that capture project-specific architecture, patterns, and domain knowledge, then keep agents-context/README.md in sync.
Concept files are general guidance, not code dumps. They describe approaches, conventions, and decision rationale so AI agents working on the project have the right context loaded for each task.
Directory layout
Concept files live in three buckets under agents-context/concepts/:
| Bucket | Purpose | Example |
|---|---|---|
domains/<domain>/ |
Business-logic concepts that span multiple source apps | domains/billing/subscription-plans-management.md |
source/<app>/ |
Stack-specific concepts tied to a single source app | source/active_snap/rspec-patterns.md |
shared/ |
True cross-cutting concerns (platform overview, infra, shared DB) | shared/architecture.md |
A file's primary owner determines its folder; source_app[] and related[] carry the multi-axis association. Maximum two levels under concepts/ — don't nest deeper.
Frontmatter contract
Every concept file opens with YAML frontmatter:
---
title: "..." # quoted; matches H1
source_app: [...] # array, even if single value
domain: <one-of> # single value from the approved domain enum
scope: [...] # array from the approved scope enum
related: [...] # other concept basenames (no path, no .md)
load_when: # 2–5 plain-language task triggers
- "..."
status: current # current | draft | deprecated
last_reviewed: YYYY-MM-DD
---
The frontmatter lets agents and tooling decide whether a concept is relevant without reading the whole file. The contract is: the README's Load-When Cheatsheet points at the file, the frontmatter confirms it's the right one, the body explains how.
agents-context/HOW_TO_CREATE_A_CONCEPT.md is the canonical authoring reference (laid down by /lead-dev-os:configure-project). If it exists in the target project, read it and defer to it when its rules diverge from this skill — it's the project's tuned authoring guide.
What ships with it
1 file 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.
- 6d ago First seen · 347 lines · 46 tokens per session scan A 5f031909156b
create-or-update-concepts is a skill published in the GitHub repository CaptainMe-AI/lead-dev-os (2 stars, last pushed 16d ago), licensed MIT. It adds 46 tokens to every session and 4,986 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
org-genome-builder
Build and save a structured organizational genome — 7 markdown files across identity, decision architecture, and quality standards directories in $HOME/.ai-first-kit/ — that encodes values as decision rules, quality standards as pass/fail criteria, and communication norms. Conducts an 11-question Socratic interview to…
sync
Run /sync as the last step after a change is complete, around merge, to keep durable knowledge current. Updates root and nested AGENTS.md, reconciles the scope from repo evidence, and flags specs the change made stale. Surgical edits only: it adds lines, and rewrites single lines it owns. Never a whole section, never…
pocket-init
Onboards an existing (brownfield) project onto Pocket. Scans the codebase and writes a project memory file (CLAUDE.md or AGENTS.md), optionally enables Pocket Enterprise (mode init) and scaffolds GitHub issue/PR templates. Trigger on "pocket-init", "set up pocket", "onboard this project", "generate CLAUDE.md", "enable…
session-recap
Document Claude Code sessions by extracting knowledge into cross-referenced documentation. Triggers on "recap the session", "summarize the work", or after significant code changes.
knowledge-bank-lookup
Delegates knowledge bank lookups to Explore subagents with reflections-first strategy that learns from past mistakes. Checks /reflections/ directory before documentation to extract documented failures to avoid and proven approaches to apply. Automatically triggers when user mentions services ([project-a], [project-b]…
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…