skill-source-citations

skill-source-citations is a skill for Claude Code from Arenukvern/skill_steward. It costs 57 tokens per session (641 once invoked), scanned A, a copy of skill-source-citations, MIT.

A procedure for recording the sources behind an Agent Skill, such as documentation, research papers, or other repositories.

In plain words
What is it for?
Use it when creating or editing skills, researching skill conventions, reviewing source coverage, and maintaining a references/sources.md file with links and provenance.
Why use it?
It prevents important claims and borrowed knowledge from becoming impossible to verify later.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Codex.

Part of the skill-steward plugin — 15 skills shipped together

Good fit Use it when creating or editing skills, researching skill conventions, reviewing source coverage, and maintaining a references/sources.md file with links and provenance.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/arenukvern/skill_steward/skill-source-citations
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 Arenukvern/skill_steward --skill skill-source-citations
Clone the repo
git clone --depth 1 https://github.com/Arenukvern/skill_steward

Made for: Claude Code.

Or install skill-steward, the plugin that ships this one along with the rest of its 15 skills.

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 skill-source-citations

README.md
[![agentmods](https://agentmods.dev/badge/skills/arenukvern/skill_steward/skill-source-citations.svg)](https://agentmods.dev/skills/arenukvern/skill_steward/skill-source-citations)
Your own site
<a href="https://agentmods.dev/skills/arenukvern/skill_steward/skill-source-citations"><img src="https://agentmods.dev/badge/skills/arenukvern/skill_steward/skill-source-citations.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 641 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 100% copy Near-identical to another mod 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 $0.00057 $0.00641
Opus 5 $0.00028 $0.00320
Sonnet 5 $0.00011 $0.00128
Haiku 4.5 $0.00006 $0.00064

Measured 8d ago against content hash effe2e997841, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

skill-source-citations 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.

Origin

This is a copy

100% identical to skill-source-citations — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/skill-source-citations/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill source citations

Rule: Knowledge borrowed from docs, papers, other repos, or chat research must be saved as links in the skill tree—not only in conversation.

When to use

  • Creating or editing any skills/{name}/SKILL.md
  • Researching harness/MCP/marketplace patterns before writing a skill
  • Reviewing a PR that adds procedural claims without sources

Per-skill file (required in skill_steward)

Maintain skills/{name}/references/sources.md:

# Sources

| Topic | URL | Used for |
|-------|-----|----------|
| Agent Skills spec | https://agentskills.io/ | Frontmatter rules |
| … | … | … |

## Changelog

- 2026-05-29: initial citations

Template: citation-template.md.

Workflow (create or update skill)

  1. Before writing — list URLs you will rely on in references/sources.md (can start sparse).
  2. In SKILL.md — link to spec/docs inline where non-obvious; prefer references/ for long material.
  3. After research — append new rows + changelog entry; never leave “we read X” only in chat.
  4. In PR — one line in description: “Sources updated in references/sources.md.”
  5. Validatepnpm run validate warns if sources.md is missing.

What to cite

Cite Example
Official specs agentskills.io, Cursor/Claude/Codex docs
Papers / research SkillOpt, SkillsBench arXiv
Reference implementations product MCPs, Codex plugin-eval
Blog/guides Only if procedure is non-obvious; prefer primary docs

Do not cite ephemeral chat URLs or private tokens.

Cross-skill index

Guild-wide references: docs/STANDARDS.mdx, DESIGN_FAQ.mdx.

Task Skill
Scaffold skill skill-authoring-lifecycle
Evaluate / improve skill-eval-improve
Spec audit skill-authoring-lifecycle

Sources discipline (this skill)

See references/sources.md.

Read the full file on GitHub · 81 lines

Files

What ships with it

2 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. 8d ago First seen · 81 lines · 57 tokens per session scan A effe2e997841

Subscribe to this mod's changes

skill-source-citations is a skill published in the GitHub repository Arenukvern/skill_steward (11 stars, last pushed 23d ago), licensed MIT. It adds 57 tokens to every session and 641 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to skill-source-citations, differing in 0 lines, and is treated as a copy.