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.
npx skills add po4yka/llm-wiki-skills --skill llm-wiki-provenancegit clone --depth 1 https://github.com/po4yka/llm-wiki-skillsWrote 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.
[](https://agentmods.dev/skills/po4yka/llm-wiki-skills/llm-wiki-provenance)<a href="https://agentmods.dev/skills/po4yka/llm-wiki-skills/llm-wiki-provenance"><img src="https://agentmods.dev/badge/skills/po4yka/llm-wiki-skills/llm-wiki-provenance/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.
<a href="https://agentmods.dev/skills/po4yka/llm-wiki-skills/llm-wiki-provenance"><img src="https://agentmods.dev/badge/skills/po4yka/llm-wiki-skills/llm-wiki-provenance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00065 | $0.00722 |
| Opus 5 | $0.00032 | $0.00361 |
| Sonnet 5 | $0.00013 | $0.00144 |
| Haiku 4.5 | $0.00006 | $0.00072 |
Grade A, and why
llm-wiki-provenance 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LLM-Wiki Provenance
Goal
Make important wiki claims traceable to raw sources or clearly mark them as unsupported, inferred, or ambiguous.
When to use
- A page has claims with no visible link back to
raw/sources or source pages. - A generated summary cites another generated summary instead of an original source.
- Support labels (extracted, inferred, synthesis, unsupported) look wrong or are missing.
- The user asks for a provenance gap report before assigning stable IDs.
- Current-state or status claims need re-verified evidence rather than an assumed link.
- Do not use this skill to insert stable IDs; hand that off to
llm-wiki-claim-anchors.
Inputs
- Target pages or folders.
raw/andwiki/locations.- Existing source pages, hashes and frontmatter if present.
- Desired mode: report-only or patch.
Procedure
1. Select provenance level
Use the smallest useful level:
| Level | Meaning |
|---|---|
| source-level | Page links to the source page or raw source. |
| claim-level | Individual claims link to supporting source sections or anchors. |
| audit-ready | Claims include source path, hash, date, model, confidence and review state. |
2. Extract claims
For each target page, identify factual claims, recommendations, current-state statements and synthesis claims.
Classify support:
extracted | inferred | ambiguous | synthesis | unsupported | conflicting
Use extracted for claims directly stated in inspected sources. Use synthesis only for editorial conclusions drawn across sources; keep the source links visible.
3. Locate evidence
Search source pages and raw sources. Do not invent evidence. If evidence is not found, mark a gap instead of rewriting the claim.
4. Produce provenance patches
In patch mode, add backlinks near claims using the vault's preferred style. Examples:
- Claim text. Source: [[sources/source-title#section]]
or frontmatter:
source_paths:
- raw/sources/example.md
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.
- 12d ago First seen · 112 lines · 65 tokens per session scan A 190b2ea0c64a
llm-wiki-provenance is a skill published in the GitHub repository po4yka/llm-wiki-skills (3 stars, last pushed 19d ago), licensed MIT. It adds 65 tokens to every session and 722 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 2026-08-31.
Other skills, from other repositories
okf-harness-bootstrap
This unified entrypoint routes setup and workspace maintenance without making the user choose a mode.
okf-harness
One Door routes OKF Harness workspace requests to exactly one internal workflow at a time.
wiki-lint
Health-check a wiki vault. Finds orphan pages (no inbound links), dead wikilinks (point to non-existent pages), missing frontmatter fields, stale claims, empty sections, and pages absent from catalog.md. Produces a structured report with severity tiers and proposes concrete fixes — but does not auto-apply them unless…
meta-sync-template
Interactive flow to propagate the reference (.template) vault's plugins, snippets, and root docs to one or more configured vaults. Reads the active router config, lists every vault with online status, flags vaults missing obsidian-local-rest-api upfront, lets the user pick all or a subset, and optionally re-clones…
save
File the current Claude conversation (or a specific insight from it) as a structured wiki note. Auto-detects the right type (decision, answer, session-log, technique, ADR), writes appropriate frontmatter, places the file in the correct wiki folder, and updates catalog.md, journal.md, hot.md. Use when the user says…
wiki-boundary
Rank the "frontier" pages of a wiki — the crossroads many pages link to that stay thin inside — so you can decide where research would pay off most. Use when the user says "what should I write about next", "where are the gaps", "which pages need work", "find the thin hub pages", "boundary pages", "/wiki-boundary"…