knowledge-mcp: Skill for Claude Code

.claude/skills/plan/SKILL.md

plan is a skill for Claude Code from fulminate-io/knowledge-mcp. It costs 79 tokens per session (1,346 once invoked), scanned A, original, Apache-2.0.

A planning tool that researches a codebase and records a structured, phased implementation plan with success criteria in a knowledge store. It is intended for features, refactors and other multi-step work.

In plain words
What is it for?
Use it to inspect relevant code and project decisions, define the files and order of work, connect the plan to its parent ticket, and record how completion will be checked.
Why use it?
It turns an approved task into an ordered set of implementation steps grounded in the existing code. It also exposes missing requirements or architectural questions before coding begins.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

This is fulminate-io/knowledge-mcp's own configuration. It tells Claude Code how to work on knowledge-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything knowledge-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to fulminate-io/knowledge-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/fulminate-io/knowledge-mcp/main/.claude/skills/plan/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/fulminate-io/knowledge-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for plan

README.md
[![agentmods](https://agentmods.dev/badge/skills/fulminate-io/knowledge-mcp/plan/github.svg)](https://agentmods.dev/skills/fulminate-io/knowledge-mcp/plan)
Your own site
<a href="https://agentmods.dev/skills/fulminate-io/knowledge-mcp/plan"><img src="https://agentmods.dev/badge/skills/fulminate-io/knowledge-mcp/plan/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.

agentmods 80×15 button for plan

Your own site · 80×15
<a href="https://agentmods.dev/skills/fulminate-io/knowledge-mcp/plan"><img src="https://agentmods.dev/badge/skills/fulminate-io/knowledge-mcp/plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,346 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00079 $0.01346
Opus 5.5 $0.00032 $0.00538
Sonnet 5.5 $0.00016 $0.00269
Haiku 4.5 $0.00008 $0.00135

Measured 1mo ago against content hash 069ece212c04, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

plan 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.

.claude/skills/plan/SKILL.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prefill: $ARGUMENTS

For pipeline discipline (background spawns, one writer per artifact, verdict routing) reference /orchestrate. This skill is prefill-specific.

Step 0: Gate on the ticket

Fetch the ticket by id with metadata. metadata.validated must be present and name a research node; without it, stop and route to /research. Read the ticket's open items: an undecided design the user owns is settled with the user before a planner spawns, never left for the planner.

manage({"operation":"status"}); collect if the index is behind the tree the ticket lands on.

Step 1: Spawn the planner (background)

One planner, one prefill. The brief carries the ticket id, the tree and branch to resolve at, sibling work in flight on the same branch with its touched files, the user's load-bearing rules verbatim, and the reads to stamp. It names no design and no mechanism.

Agent(subagent_type: "planner",
      prompt: "Produce the prefill for ticket <id> at <tree> on <branch>, per the prefill rulebook: no steps, every line resolved by tool with its command, the what-to-test list covering every numbered requirement, the harnesses that reach each seam. Siblings in flight: <list or none>. Deliver the report to main.",
      description: "Prefill: <ticket>",
      run_in_background: true)

Step 1a: Settle open items before anything freezes

When the planner's report carries open items, settle every one the ticket, the user's rules or memory already answers, and route the rest to the user, before resolving citations. Each settlement goes back to the planner that raised it, idle with its context intact, to incorporate into the prefill. The prefill is not frozen for review until that planner has read the settlement back into the node. At reviewer spawn the ticket's updated_at is older than the prefill's, or the prefill goes back to the planner first. A ticket amendment after that point reopens the prefill, never the audit.

Read the full file on GitHub · 108 lines

Changes

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.

  1. 1mo ago Changed · +11 lines · +11 tokens per session 069ece212c04
  2. 1mo ago Changed · -118 lines · +25 tokens per session a36efd0e4802
  3. 2mo ago First seen · 215 lines · 43 tokens per session scan A b49c2dfdda91

Subscribe to this mod's changes

plan is a skill published in the GitHub repository fulminate-io/knowledge-mcp (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 79 tokens to every session and 1,346 once invoked, about $0.0003 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.

Related

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…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

vercel/next.js · 95 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 83 tokens