knowledge-mcp: Skill for Claude Code

.claude/skills/knowledge-tools/SKILL.md

knowledge-tools is a skill for Claude Code from fulminate-io/knowledge-mcp. It costs 64 tokens per session (1,981 once invoked), scanned A, original, Apache-2.0.

An internal rulebook for AI coding agents that tells them which tools to use for different questions. It puts stored project knowledge first and uses the shell only when needed.

In plain words
What is it for?
It guides agents through recalling past work, checking the knowledge graph, choosing approved shell commands, and recording the tools used in each report.
Why use it?
It prevents agents from relying on incomplete searches, remembered citations, or one failed lookup when the project already contains relevant findings and decisions.

Skill for Claude Code

Written for Claude Code: user-invocable 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/knowledge-tools/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 knowledge-tools

README.md
[![agentmods](https://agentmods.dev/badge/skills/fulminate-io/knowledge-mcp/knowledge-tools.svg)](https://agentmods.dev/skills/fulminate-io/knowledge-mcp/knowledge-tools)
Your own site
<a href="https://agentmods.dev/skills/fulminate-io/knowledge-mcp/knowledge-tools"><img src="https://agentmods.dev/badge/skills/fulminate-io/knowledge-mcp/knowledge-tools.svg" alt="Measured on agentmods" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,981 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 $0.00064 $0.01981
Opus 5 $0.00032 $0.00991
Sonnet 5 $0.00013 $0.00396
Haiku 4.5 $0.00006 $0.00198

Measured today against content hash 0dcfdcbd155b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

knowledge-tools 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 today.

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/knowledge-tools/SKILL.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

KNOWLEDGE-TOOLS — the graph answers first; the shell is the fallback

Why this rulebook exists

Lanes that live in the shell produce artifacts one step removed from the truth: a citation typed from memory, a caller list from a grep that cannot see interface dispatch, a "does not exist" from one miss, a mechanism asserted without recalling that the graph already recorded it. The graph is indexed, call-graph-aware, and carries every decision, finding and thought from every prior session. Measured lanes that answered code questions with two hundred shell calls and four graph calls delivered the plans that failed audit. The order below is prescriptive, not advisory.

The question-to-call table

Ask the question; make the call named for it; go to the shell only when the table sends you there.

The question The call
What did prior sessions learn, decide or rule about this? thoughts({operation:"recall", query:"<topic>"}) then search({graph:"knowledge", queries:[...]}); hydrate hits with query({ids:[...], fields:["summary","content"]})
What was decided, and why? query({type:"decision", text:"<topic>"}); query({mode:"evidence", id:"<decision>"})
Where is X, what is X named, does anything like X exist? search({graph:"code", repo:"<repo>", queries:[3 to 5 phrasings]})
Does code SHAPED like this exist, and where? ast({operation:"match", language:"<lang>", pattern:"<dsl>", where:{...}}); size first with operation:"count"
Who calls X; what does X call? traverse({start:"<id copied from a search or file_symbols hit>", graph:"code", repo:"<repo>", edge_types:["CALLS"], direction:"in"}) plus an ast shape match with include_tests:true. The start id is COPIED from a hit, never composed from a remembered file name; a not found names your id, not the graph, so search the symbol and copy the id it returns
What is in this file? query({mode:"file_symbols", ...}) or file_symbols, then Read the specific range
Every site that does X across the tree (a census) ast({operation:"count"}) then match, package_prefixes to scope, output pasted as the census
Every occurrence of an exact literal: a string, a status word, a metadata key, a name ast({operation:"count", language:"<lang>", pattern:"\"<literal>\""}) then match; a quoted literal is a pattern and matches the literal node wherever it appears, with a by-file count
Which files carry a build constraint, or any question about comment text The shell: grep for the constraint or the comment text, recorded in the census as such. A comment pattern compiles in the DSL but matches no comment node, so this is an allowlisted shell class, not a fallback
Which checks cover the shapes I touch? manage_checks({operation:"run", language:"<lang>", repo:"<abs path>", ids:[...]}); read the hits
A structural requirement: a shape that must, or must never, appear manage_checks({operation:"create", language, name, summary, description, check_type:"ast_pattern", dsl_pattern, check_where, severity, fixture_bad, fixture_good}); admission fires on the bad fixture and stays silent on the good one; then run it over the tree
How much did a lane spend, and on which tools? analyze_usage({operation:"run-detectors", scope:"single", agent:"<lane id>"}) (orchestrator)
The idiom or pattern for this mechanism search({graph:"practice", language:"all", queries:[...]})
The node types and edge types a graph carries query({mode:"stats", graph:"<family>"})
A plan, ticket or project's shape query({mode:"plan_tree", id:"..."}) then query({ids:[...], fields:[...]}) for bodies and metadata
Why a node is in an unexpected state query({mode:"examine", id:"..."})
An external API, library or provider behavior WebSearch / WebFetch the pinned version's documentation, never a remembered shape
A uniform structural rewrite across files ast({operation:"replace", ..., dry_run:true}), read the diff, then dry_run:false

Read the full file on GitHub · 119 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. today First seen · 119 lines · 64 tokens per session scan A 0dcfdcbd155b

Subscribe to this mod's changes

knowledge-tools is a skill published in the GitHub repository fulminate-io/knowledge-mcp (1 stars, last pushed yesterday), licensed Apache-2.0. It adds 64 tokens to every session and 1,981 once invoked, about $0.0003 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 2026-09-07.

Related

Other skills, from other repositories

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens

establishing-project-context

Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.

GanyuanRan/Aegis · 45 tokens