A repository investigation workflow that builds explanations of why systems exist and behave as they do. It links claims such as “X because Y” to evidence from code and other sources.

Investigating architectural reasons, tracing causes across a repository, and recording evidence-backed explanations.

It helps uncover the causes behind non-obvious code and system behavior instead of only describing what the code does.

How fulminate-io/knowledge-mcp configures Claude Code

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/explore/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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/fulminate-io/knowledge-mcp/explore/github.svg)](https://agentmods.dev/skills/fulminate-io/knowledge-mcp/explore)

Your own site

<a href="https://agentmods.dev/skills/fulminate-io/knowledge-mcp/explore"><img src="https://agentmods.dev/badge/skills/fulminate-io/knowledge-mcp/explore/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/fulminate-io/knowledge-mcp/explore"><img src="https://agentmods.dev/badge/skills/fulminate-io/knowledge-mcp/explore.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,572 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.

Model	Per session	Once invoked
Fable 5.1	$0.00058	$0.01572
Opus 5.5	$0.00023	$0.00629
Sonnet 5.5	$0.00012	$0.00314
Haiku 4.5	$0.00006	$0.00157

Measured 1mo ago against content hash e628ba58195f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

explore 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/explore/SKILL.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Explore: $ARGUMENTS

For universal orchestration discipline reference /orchestrate. This skill is causal-investigation-specific.

You are building causal context about the repo. Output: thoughts — each a single "X because Y" claim — linked via EdgeBecause. Clusters are emergent (computed over the thought graph and its because-edges by the periodic propagation pass). Authoring lives in session explore-<topic-slug>; no container node.

Other systems answer what and how; this one answers why.

Delegate heavy lifting to the explorer agent. It's optimized for causal investigation, cross-graph evidence wiring, and the 5-test non-triviality discipline. This skill orchestrates the run + user-approval loop.

Step 0: Index Freshness

manage({ "operation": "status" })

If behind HEAD, prompt user to reindex. Causal claims are only as trustworthy as the evidence they cite — stale index → stale claims.

Step 0.5: Recall Existing Exploration

thoughts({ "operation": "recall", "query": "$ARGUMENTS", "session": "explore-*" })

Three things to check:

Existing thoughts covering same ground — semantic match → user may want to extend (new thought + because-link) or supersede (new with branches_from, prior invalidated).
Previously rejected candidates — session: "explore-rejected-candidates" lists past noise; don't re-propose.
Invalidated thoughts with fresh evidence — cited code/rule/decision has since changed → supersede-on-refresh candidate.

Step 1: Choose the Mode

Read the full file on GitHub · 142 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.

1mo ago Changed e628ba58195f
2mo ago First seen · 142 lines · 58 tokens per session scan A eec0203ad4c9

Subscribe to this mod's changes

explore is a skill published in the GitHub repository fulminate-io/knowledge-mcp (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 58 tokens to every session and 1,572 once invoked, about $0.0002 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.

Research

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

knowledge-mcp: Skill for Claude Code