What is skilljack-docs?

Documentation for Skilljack, an MCP server that makes a catalogue of agent skills available to a language model. It explains the server's tools, configuration, skill discovery, and internal design.

Use it to configure Skilljack, choose how skills are discovered, understand its MCP tools and resources, and integrate it with an MCP client.

It helps developers understand how Skilljack delivers and refreshes skills, including the difference between automatically updated and fixed skill lists. This reduces guesswork when setting up or troubleshooting the server.

skilljack-docs — Skill for Claude Code and Codex by olaservo

Install

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.

Any agent

npx skills add olaservo/skilljack-mcp --skill skilljack-docs

Clone the repo

git clone --depth 1 https://github.com/olaservo/skilljack-mcp

Made for: Claude Code, Codex.

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/olaservo/skilljack-mcp/skilljack-docs/github.svg)](https://agentmods.dev/skills/olaservo/skilljack-mcp/skilljack-docs)

Your own site

<a href="https://agentmods.dev/skills/olaservo/skilljack-mcp/skilljack-docs"><img src="https://agentmods.dev/badge/skills/olaservo/skilljack-mcp/skilljack-docs/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/olaservo/skilljack-mcp/skilljack-docs"><img src="https://agentmods.dev/badge/skills/olaservo/skilljack-mcp/skilljack-docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 7,921 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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	$0.00026	$0.07921
Opus 5.5	$0.00010	$0.03168
Sonnet 5.5	$0.00005	$0.01584
Haiku 4.5	$0.00003	$0.00792

Measured 8d ago against content hash a8082721c5d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

skilljack-docs 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 8d 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.

skills/skilljack-docs/SKILL.md · 570 lines

How it starts

The opening of the file, as written. The whole thing — 570 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skilljack MCP Documentation

An MCP server that jacks Agent Skills directly into your LLM's brain.

Skill changes: on stdio the default catalog is sent once, at initialize, so added or removed skills reach the model's catalog after a restart. Prompts and resources refresh live through listChanged notifications. Use --static for a fixed skill set.

Tool search / deferred tools. By default, skilljack delivers its skill catalog via MCP server instructions, which arrive in the initialize handshake and reach the model even when tool search / deferred tool loading is enabled (the default on modern Claude Code, ~2.1.x) — automatic skill activation works out of the box. The legacy --catalog=tool-description mode (not recommended) delivers the catalog inside the load-skill tool description instead, but tool-search clients defer MCP tool descriptions out of context, so that mode requires disabling tool search (e.g. ENABLE_TOOL_SEARCH=false) for auto-activation. See Catalog Delivery.

Features

Dynamic Skill Discovery - Watches skill directories and automatically refreshes when skills change
Multiple Sources - Local directories, GitHub repositories, and .well-known/agent-skills/ publishers (both allowlisted)
Tool List Changed Notifications - Sends tools/listChanged so clients can refresh available skills
load-skill Tool - Load full skill content on demand (progressive disclosure)
MCP Prompts - Load skills via /skill prompt with auto-completion or per-skill prompts
MCP Resources - Access skills via skill:// URIs aligned with SEP-2640
Skills extension (SEP-2640) - Declares io.modelcontextprotocol/skills and serves skills/list / skills/get entries with verbatim frontmatter and per-file SHA-256 digests, so a skills-aware host can verify every file it reads
Resource Subscriptions - Real-time file watching with notifications/resources/updated
Configuration UI - Manage skill directories through an interactive UI in supported clients

Read the full file on GitHub · 570 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.

8d ago Changed · +2 lines a8082721c5d6
1mo ago Changed · +37 lines 85ea9b01f1ec
1mo ago Changed · +2 lines 935cccafa4bf
1mo ago Changed · +41 lines d79bd3375ea5
2mo ago First seen · 488 lines · 26 tokens per session scan A 2eb52964709c

Subscribe to this mod's changes

skilljack-docs is a skill published in the GitHub repository olaservo/skilljack-mcp (21 stars, last pushed 5d ago), licensed MIT. It adds 26 tokens to every session and 7,921 once invoked, about $0.0001 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 2026-08-30.

Building agents Writing and docs

skilljack-docs next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
skilljack-docsolaservo/skilljack-mcp	Skill	21	5d ago	MIT	A	26	Claude Code, Codex
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code