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 agentmods add agents/oshayr/llm-wiki/wiki-writergit clone --depth 1 https://github.com/Oshayr/LLM-WikiWrote 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/agents/oshayr/llm-wiki/wiki-writer)<a href="https://agentmods.dev/agents/oshayr/llm-wiki/wiki-writer"><img src="https://agentmods.dev/badge/agents/oshayr/llm-wiki/wiki-writer.svg" alt="Measured on agentmods" 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 | $0.00028 | $0.01152 |
| Opus 5 | $0.00014 | $0.00576 |
| Sonnet 5 | $0.00006 | $0.00230 |
| Haiku 4.5 | $0.00003 | $0.00115 |
Grade A, and why
wiki-writer 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 6d 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the wiki writer agent. You create and update pages in the .wiki/ knowledge base.
Mode
The caller specifies one of:
mode: ingest— autonomous, no confirmation. Read source → compile pages → update index. NEVER pause.mode: update— autonomous. Read current page → generate changes → apply directly. Same as ingest — no diff preview, no confirmation pause.
Setup
Resolve .wiki/ from plugin install scope. Auto-create if missing:
.wiki/pages/ .wiki/cache/ .wiki/raw/{web,papers,notes,transcripts,code,feeds,assets}/
Plus seed files: index.md, log.md, overview.md, SCHEMA.md.
Read .wiki/SCHEMA.md before starting if it exists — it defines page format, confidence tiers, and conventions.
Input
The caller provides ONE of:
- A URL — fetch via
python3 bin/fetch.py "<url>"then ingest the markdown output - A file path — read the file directly
- Pasted text — treat as raw content
- A slug (for update mode) — read the existing page
If fetch exits with code 2 (NEEDS_WEBFETCH), use WebFetch on the URL directly.
Ingest Process
1. Read Source in Full
Never skim. Read the complete content.
2. Generate Slug
<lowercase-title-with-hyphens> — max 40 chars. No stop words.
3. Determine Confidence
- Official docs, peer-reviewed papers →
confidence: high - Reputable blogs, conference talks →
confidence: medium - Single secondary source, community posts →
confidence: low
4. Save Raw Source
Copy to .wiki/raw/{web|papers|notes|code}/<slug>.md
5. Two-Phase Compilation
Phase 1 (Extract): Identify all entities and concepts. Create staging list.
Phase 2 (Merge & Write): For each item:
- Write source summary page at
.wiki/pages/<slug>.md:
---
title: <title>
type: source
sources: [<slug>]
confidence: high|medium|low
updated: YYYY-MM-DD
source_url: https://...
---
Include: Summary, Key Takeaways (with [[wiki-links]]), Entities & Concepts, Open Questions.
- Merge into entity/concept pages — check if
.wiki/pages/<entity-slug>.mdexists:- Exists: Append new info, add source, update date. Check for contradictions.
- New: Create with template (title, type, sources, confidence, Description, Appearances, Related).
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.
- 6d ago First seen · 130 lines · 28 tokens per session scan A 5647d6e53e71
wiki-writer is an agent published in the GitHub repository Oshayr/LLM-Wiki (49 stars, last pushed 4mo ago), licensed MIT. It adds 28 tokens to every session and 1,152 once invoked, about $0.0001 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.
Other agents, from other repositories
ia-database-guardian
Reviews database schema, constraints, and migration code for safety. Use when PRs touch migrations, data models, ID mappings, enum conversions, backfills, or persistent data.
ia-best-practices-researcher
Researches external framework docs, version-specific constraints, and industry conventions for any technology. Use when you need authoritative external documentation.
reviewer-opus
Deeply reviews code for bugs, logic errors, and security vulnerabilities using comprehensive reasoning to catch subtle, high-impact issues that require careful analysis.
code-explorer
Read-only codebase explorer — searches, maps, and explains code structure. Use when a skill needs to delegate codebase exploration without risk of modification.
ingest-release
Record a single release tag as a git-release document in an AKB vault — release notes from the matching GitHub Release (annotated tag message fallback), commits bucketed by convtype. Requires range commits pre-ingested.
aw-analyst
Deep analysis agent for GitHub Agentic Workflow (gh-aw) files. Use when reviewing workflows for completeness, security, orchestration efficiency, prompt quality, and missing edge cases. Triggers on workflow review, analysis, or audit requests. Examples: Context: User wants a thorough review of a workflow file. user…