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 bartolli/kmd --skill intentgit clone --depth 1 https://github.com/bartolli/kmdWrote 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/bartolli/kmd/intent)<a href="https://agentmods.dev/skills/bartolli/kmd/intent"><img src="https://agentmods.dev/badge/skills/bartolli/kmd/intent/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/bartolli/kmd/intent"><img src="https://agentmods.dev/badge/skills/bartolli/kmd/intent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00185 | $0.02682 |
| Opus 5.5 | $0.00074 | $0.01073 |
| Sonnet 5.5 | $0.00037 | $0.00536 |
| Haiku 4.5 | $0.00018 | $0.00268 |
Grade A, and why
intent 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 — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Intent — Grill the Idea Against the Wiki
Interview the user relentlessly about every aspect of a project's intent until you reach a shared understanding. Walk down each branch of the design tree, resolving dependencies one-by-one. For each question, provide your recommended answer.
Ask one question at a time, waiting for feedback before continuing.
If a question can be answered by exploring the codebase or wiki, explore instead of asking.
Prerequisites
Before grilling, the project must declare WIKI_SCOPE: <scope> in its project instructions (AGENTS.md or the harness's equivalent). If missing, suggest /wiki first and stop.
Mode detection
Read projects/<scope>/index.md in the vault:
- Greenfield — file does not exist. Scaffold the scope from scratch (intent capture → identity → primer stub → methodology → vocabulary → lazy ADRs).
- Brownfield — file exists. Refine intent, cross-reference code (if any), surface contradictions between user's stated model and code/spec reality, sharpen
glossary.mdand ADRs as the conversation reveals them.
Announce the mode you're running in before starting.
New-scope guardrail: if <scope> is not in vault.yaml's scopes: field, STOP. New scopes need explicit user approval. Surface the current scope list and ask.
Greenfield flow
Step 1 — Identity (lands in index.md)
Collect, one question at a time:
- Title — What does this project deliver, in one phrase? (Recommend: short, noun-phrase form, e.g. "Operations system for a food truck")
- Summary — What is it, in one or two sentences? (Recommend: extract from the user's first description; show your draft.)
- Methodology —
sdd(spec-driven),tdd(test-driven), orhybrid? (Recommendhybridfor app-layer work,sddfor spec-heavy or contract-first work,tddwhen the surface is mostly behavior-discoverable. State your reasoning per project.) - Phase — what number? (Recommend
0for greenfield,1if a working prototype exists.) - Tags — pick 3-6 from existing
top_tagsifprime(<scope>)is callable (MCP tool, orkmd prime <scope>); otherwise propose new ones with justification.
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.
- 1mo ago Changed aa2454e993da
- 1mo ago Changed 96b961e3b409
- 1mo ago First seen · 246 lines · 185 tokens per session scan A 276c26d4b81c
intent is a skill published in the GitHub repository bartolli/kmd (7 stars, last pushed 1mo ago), licensed MIT. It adds 185 tokens to every session and 2,682 once invoked, about $0.0007 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 2026-09-04.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…