A tool for adding source citations to wiki pages, either by finding sources for unsupported claims or by saving a quote and URL as a citation.

Use it to review uncited claims, suggest sources, ingest a URL, and add citation tokens to wiki pages.

It helps prevent factual statements from being left without sources and keeps references in a consistent format.

wiki-cite — Skill for Claude Code and Codex by badwally: A tool for adding source citations to wiki pages…

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/badwally/theknowledge/wiki-cite

Any agent

npx skills add badwally/TheKnowledge --skill wiki-cite

Clone the repo

git clone --depth 1 https://github.com/badwally/TheKnowledge

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/badwally/theknowledge/wiki-cite.svg)](https://agentmods.dev/skills/badwally/theknowledge/wiki-cite)

Your own site

<a href="https://agentmods.dev/skills/badwally/theknowledge/wiki-cite"><img src="https://agentmods.dev/badge/skills/badwally/theknowledge/wiki-cite.svg" alt="Measured on agentmods" height="20"></a>

Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 776 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5	$0.00063	$0.00776
Opus 5	$0.00032	$0.00388
Sonnet 5	$0.00013	$0.00155
Haiku 4.5	$0.00006	$0.00078

Measured 3d ago against content hash 74f67ac02150, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

wiki-cite 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 3d 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/wiki-cite/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

What This Does

Two modes:

Mode A — Fix citations on an existing page: Surfaces uncited claims, runs wiki cite-suggest, confirms with you, writes [[sources/<id>]] tokens.

Mode B — Capture-to-cite from any repo (AGT-7): Takes a quote + URL from anywhere in ~/code/*, ingests the source if not already present, auto-picks the target wiki page, and adds the citation — one operation via MCP.

Reference conventions: WIKI.md § 6 (citation format), § 9 rule 3 (citation grounding).

Usage

# Mode A — fix citations on an existing page
/wiki-cite wiki/synthesis/glp1-hunger.md
/wiki-cite wiki/concepts/food-noise.md --claim "Food noise is..."

# Mode B — capture from another project
/wiki-cite "Food noise is a persistent mental chatter about food" https://example.com/paper
/wiki-cite "GLP-1 reduces food noise" https://pubmed.ncbi.nlm.nih.gov/12345 wiki/concepts/food-noise.md

Execution — Mode A (fix existing page)

Read the page: Identify claims without [[sources/...]] citation tokens.

Run cite-suggest:

.venv/bin/wiki cite-suggest wiki/<type>/<slug>.md

Review candidates: Show top 1-2 candidates per uncited claim. Confirm.

Write citations (one at a time):

.venv/bin/wiki cite-add wiki/<type>/<slug>.md --claim "<claim text>" --source <id>

Validate:

.venv/bin/wiki finalize wiki/<type>/<slug>.md

Execution — Mode B (capture-to-cite)

Single MCP call via wiki_cite_capture:

wiki_cite_capture(
    quote="<the claim text>",
    url="<source URL>",
    target_page="wiki/concepts/<slug>.md",  # omit for auto-pick
)

Or CLI:

.venv/bin/wiki cite-capture "<quote>" <url> [--target wiki/<type>/<slug>.md]

What happens:

URL looked up in raw/ — reused if already ingested (idempotent).
If not present: wiki ingest <url> --draft pulls it in.
wiki/sources/<id>.md backfilled if filter excluded it.
Target page auto-picked by token-overlap if not specified.
wiki cite-add adds [[sources/<id>]] to the matching claim line.

Read the full file on GitHub · 83 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.

3d ago First seen · 83 lines · 63 tokens per session scan A 74f67ac02150

Subscribe to this mod's changes

wiki-cite is a skill published in the GitHub repository badwally/TheKnowledge (23 stars, last pushed 1mo ago), licensed MIT. It adds 63 tokens to every session and 776 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 2026-08-30.

Research Writing and docs

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 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