sourcey

sourcey is a skill for Claude Code, Codex from runxhq/runx. It costs 12 tokens per session (4,900 once invoked), scanned A, original, Apache-2.0.

A documentation-building workflow that uses Sourcey to turn Markdown, OpenAPI specifications, Doxygen XML, or MCP server snapshots into a static HTML documentation site.

In plain words
What is it for?
It helps discover a project's documentation scope, create or update its source and configuration, build the site, and verify the result.
Why use it?
It organizes the documentation build, review, revision, and verification so the generated site can be checked before delivery.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/runxhq/runx/sourcey
Any agent
npx skills add runxhq/runx --skill sourcey
Clone the repo
git clone --depth 1 https://github.com/runxhq/runx

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.

agentmods badge for sourcey

README.md
[![agentmods](https://agentmods.dev/badge/skills/runxhq/runx/sourcey.svg)](https://agentmods.dev/skills/runxhq/runx/sourcey)
Your own site
<a href="https://agentmods.dev/skills/runxhq/runx/sourcey"><img src="https://agentmods.dev/badge/skills/runxhq/runx/sourcey.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,900 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
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 $0.00012 $0.04900
Opus 5 $0.00006 $0.02450
Sonnet 5 $0.00002 $0.00980
Haiku 4.5 $0.00001 $0.00490

Measured yesterday against content hash 389599a894d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sourcey scanned grade A with 1 finding 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 yesterday.

The scan reads SKILL.md. This mod also ships 1 executable file (harness/seed_workspace.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

codeSamples: ["curl", "javascript", "python"], // for OpenAPI tabs
skills/sourcey/SKILL.md · 490 lines

How it starts

The opening of the file, as written. The whole thing — 490 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sourcey

Generate a documentation site for a project using Sourcey. Sourcey is a static documentation generator that produces HTML sites from markdown pages, OpenAPI specs, Doxygen XML, and MCP server snapshots.

What this skill does

By default, runx executes Sourcey as a governed mixed-runner skill:

  1. discover the bounded documentation scope, evidence, and plan
  2. author the bounded docs/config bundle
  3. write the source bundle deterministically under the runner's declared workspace scopes
  4. build docs deterministically
  5. critique the built output in one bounded pass
  6. apply at most one bounded revision pass
  7. rebuild and verify the output deterministically

For already-configured projects, the same sourcey runner stays narrow: the discover step can confirm existing config, the author/revise passes can return empty bundles, and the deterministic tool steps still perform the build and verification work.

A direct zero-input invocation targets the current workspace, so runx skill sourcey reaches bounded discovery immediately. A composed chain targeting a different project should pass both project and repo_root explicitly so discovery, authored-source writes, and deterministic builds stay on the same workspace boundary.

For repository-backed projects, Sourcey owns two separate surfaces: committed docs source and generated site output. Keep those separate. Do not mix emitted HTML, search indexes, or OG assets back into the authored docs tree.

When to use this skill

  • A project needs a maintainer-grade documentation site generated from real repository evidence, existing docs, API specs, Doxygen XML, or MCP snapshots.
  • A branded package or product needs Sourcey output with governed discovery, bounded authoring, deterministic build, critique, revision, and receipt proof.
  • A workflow needs to separate authored docs source from generated site output while preserving a reviewable receipt trail.
  • A maintainer wants CI or deploy to rebuild docs without inventing scope, prose, or information architecture at deploy time.

Read the full file on GitHub · 490 lines

Files

What ships with it

6 files 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.

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. yesterday First seen · 490 lines · 12 tokens per session scan A 389599a894d9

Subscribe to this mod's changes

sourcey is a skill published in the GitHub repository runxhq/runx (84 stars, last pushed yesterday), licensed Apache-2.0. It adds 12 tokens to every session and 4,900 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

morph-ppt

Generate Morph-animated PPTs with officecli.

CES-Ltd/TitanX · 14 tokens

dynamic-resources

Example skill loaded from resourcesdiscover.

dmae97/omk · 11 tokens

officecli-pptx

Use this skill any time a .pptx file is involved -- as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file; editing, modifying, or updating existing presentations; combining or splitting slide files; working with…

CES-Ltd/TitanX · 103 tokens

officecli-financial-model

Use this skill when the user wants to build a financial model, 3-statement model, DCF valuation, cap table, scenario analysis, or financial projections in Excel. Trigger on: 'financial model', '3-statement model', 'DCF', 'cap table', 'pro forma', 'projections', 'sensitivity analysis', 'waterfall', 'debt schedule'…

CES-Ltd/TitanX · 136 tokens

officecli-docx

Use this skill any time a .docx file is involved -- as input, output, or both. This includes: creating Word documents, reports, letters, memos, or proposals; reading, parsing, or extracting text from any .docx file; editing, modifying, or updating existing documents; working with templates, tracked changes, comments…

CES-Ltd/TitanX · 114 tokens

officecli-xlsx

Use this skill any time a .xlsx file is involved -- as input, output, or both. This includes: creating spreadsheets, financial models, dashboards, or trackers; reading, parsing, or extracting data from any .xlsx file; editing, modifying, or updating existing workbooks; working with formulas, charts, pivot tables, or…

CES-Ltd/TitanX · 119 tokens