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 anh-chu/llm-wiki-pm --skill llm-wiki-prdgit clone --depth 1 https://github.com/anh-chu/llm-wiki-pmWrote 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/anh-chu/llm-wiki-pm/llm-wiki-prd)<a href="https://agentmods.dev/skills/anh-chu/llm-wiki-pm/llm-wiki-prd"><img src="https://agentmods.dev/badge/skills/anh-chu/llm-wiki-pm/llm-wiki-prd/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/anh-chu/llm-wiki-pm/llm-wiki-prd"><img src="https://agentmods.dev/badge/skills/anh-chu/llm-wiki-pm/llm-wiki-prd.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 | $0.00036 | $0.01752 |
| Opus 5 | $0.00018 | $0.00876 |
| Sonnet 5 | $0.00007 | $0.00350 |
| Haiku 4.5 | $0.00004 | $0.00175 |
Grade A, and why
llm-wiki-prd scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LLM Wiki PRD
Sub-skill of llm-wiki-pm. Generates PM artifacts (PRDs, user stories, release notes) from wiki knowledge. The wiki is the only source of truth. Never fabricates product context.
When This Skill Activates
- "write a PRD", "draft PRD for [feature/topic]"
- "create user stories", "write user stories for [feature]", "acceptance criteria"
- "generate release notes", "draft release notes", "what shipped"
Does not activate for wiki operations (ingest, update, lint, query). Those route to llm-wiki-pm.
Orient Before Any Artifact
Per AGENTS.md, orient before any write. PRD generation requires knowing what pages exist to avoid duplication and ensure grounding.
Orient steps (mandatory):
WIKI=$(cat .wiki-path 2>/dev/null | tr -d '[:space:]')
WIKI=${WIKI:-${CLAUDE_PLUGIN_OPTION_wiki_path:-${WIKI_PATH:-$(pwd)}}}
① Read $WIKI/SCHEMA.md — tag taxonomy, domain scope
② Read $WIKI/index.md — what pages exist (prevents duplicate artifacts, identifies grounding material)
③ Read last 20-30 lines of $WIKI/log.md — recent activity
④ Read $WIKI/overview.md — current synthesis state
Orient gate (enforced): if steps ①-④ are not complete in this session, refuse any write. Surface: "Need to orient first. Running now." Then orient, then proceed.
Key Constraint
Never invent product context. If the wiki has no page for a claimed feature, customer segment, or competitive context, say so and offer to create a stub first:
"No wiki page found for [X]. Draft with that gap flagged, or create a stub page first?"
Every factual claim in a generated artifact must cite [[page]] from the wiki. No citation = no claim.
Operations
Output structures for all three operations live in
references/prd-templates.md — copy the matching template when drafting.
1. PRD Draft
Trigger: "write a PRD", "draft PRD for [feature/topic]"
① Ground in wiki — grep -ri "<feature>" "$WIKI" --include="*.md" -l, then read
every relevant page: entities, concepts, comparisons, customer pages, and
decision/roadmap/question-tagged pages.
② Surface gaps before drafting — if a major section has no wiki backing
(target persona, competitive context, core problem, key decisions), flag it and
ask; never draft a fabricated section silently:
"Missing wiki coverage for: [X, Y, Z]. Draft with gaps flagged, or research first?" ③ Draft to
$WIKI/queries/prd-<feature-slug>-<YYYY-MM-DD>/README.mdusing the PRD template (references/prd-templates.md). ④ Cite inline — every factual claim cites its source ("Per [[page]]..."); an uncited claim moves to Open Questions orgaps:. ⑤ Populategaps:with unbacked sections — this surfaces in Coverage Audit. ⑥ Update navigation — add toindex.mdunderqueries/, append theprdlog line.
What ships with it
1 file 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.
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.
- 11d ago First seen · 146 lines · 36 tokens per session scan A b344f4d7495c
llm-wiki-prd is a skill published in the GitHub repository anh-chu/llm-wiki-pm (6 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 1,752 once invoked, about $0.0002 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
llm-wiki
Build and maintain a persistent, interlinked Obsidian-compatible markdown wiki using Karpathy's LLM Wiki pattern. Extension-backed with auto-generated metadata, guardrails, and 14 custom tools (+3 opt-in agent-trajectory tools).
mindbase
Maintain a persistent AI-tended research wiki. Activates when the user wants to ingest a source (PDF, URL, article, paste), capture a thought, build the wiki context, query what's already known, lint for orphans/contradictions, or maintain page conventions. Phrases include "add this to my wiki", "today I decided…"…
wiki-ingest
Process source files into synthesised wiki pages. Always use this skill when the user says /wiki-ingest, 'import these files', 'process my clippings', 'ingest this article', 'I have new articles to add', 'turn this PDF into a wiki page', 'what's in my raw/ folder', or 'what have I ingested'. Also use when the user…
wiki-lint
Health-check the wiki: scan all pages for broken wikilinks, orphaned pages, stale index entries, missing connections, em-dash violations, orphaned assets, and schema errors. Produces a dated lint report. Always use this skill when the user says /wiki-lint, mentions broken links, dead wikilinks, orphaned pages, 'what's…
wiki-crystallize
Distil a chat thread, research session, or working document into a structured wiki page capturing the current state of knowledge. Always use this skill when the user says /wiki-crystallize, 'save this to my wiki', 'capture what we've worked out', 'write this up as a wiki page', 'update my wiki from this conversation'…
wiki-integrate
Weave a wiki page into the knowledge graph: add it to index.md and add backlinks in both directions. Always use this skill when the user says /wiki-integrate, 'nothing links to this page', 'this page is an orphan', 'connect this page to related pages', 'add backlinks to this page', 'add this page to the index', or…