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 Oshayr/LLM-Wiki --skill writegit 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/skills/oshayr/llm-wiki/write)<a href="https://agentmods.dev/skills/oshayr/llm-wiki/write"><img src="https://agentmods.dev/badge/skills/oshayr/llm-wiki/write/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/oshayr/llm-wiki/write"><img src="https://agentmods.dev/badge/skills/oshayr/llm-wiki/write.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 | $0.00090 | $0.00906 |
| Opus 5.5 | $0.00036 | $0.00362 |
| Sonnet 5.5 | $0.00018 | $0.00181 |
| Haiku 4.5 | $0.00009 | $0.00091 |
Grade A, and why
wiki-write 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 2mo 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wiki Write
Add or update content in the wiki. Auto-creates .wiki/ if it doesn't exist.
Resolve .wiki/ from plugin install scope. Auto-create if missing.
Auto-Init
If .wiki/ doesn't exist, create it automatically before proceeding:
.wiki/
pages/
index.md (empty: "# Wiki Index\n\nNo pages yet.\n")
overview.md (empty: "# Overview\n\nNo content yet.\n")
log.md (empty: "# Activity Log\n")
SCHEMA.md (evaluation rules — see below)
config.yaml (empty)
cache/
raw/
web/ papers/ notes/ transcripts/ code/ feeds/ assets/
Arguments
/wiki-write <url>— fetch and ingest a web page or paper/wiki-write <file-path>— ingest a local file (text, markdown, PDF)/wiki-write "text..."— ingest pasted text/wiki-write --batch <dir>— ingest all.mdfiles in a directory/wiki-write --update <slug>— update an existing page autonomously/wiki-write --update <slug> <url>— update page with content from URL/wiki-write --refresh-stale— find and refresh stale pages based on freshness tier
Ingest (default — no --update flag)
Launch the wiki-writer agent with mode: ingest:
- Fetches content (via
bin/fetch.pychain: cache → Jina → trafilatura → WebFetch) - Saves raw source to
.wiki/raw/ - Writes source summary page and entity/concept pages to
.wiki/pages/ - Runs backlink audit via
bin/backlinks.py update .wiki/pages - Updates
.wiki/index.md,.wiki/overview.md,.wiki/log.md - No confirmation pause — runs end-to-end autonomously
Report: pages written, pages updated, confidence assigned.
Update (--update)
Launch the wiki-writer agent with mode: update:
- Reads current page
- Generates proposed changes
- Runs contradiction sweep against high-confidence pages
- Applies changes directly — same autonomous behavior as ingest
- Updates index.md and log.md
Refresh Stale (--refresh-stale)
Finds pages past their freshness tier TTL (see freshness tiers in /wiki-maintain).
For each: searches for fresh sources → applies updates autonomously.
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.
- 2mo ago First seen · 92 lines · 90 tokens per session scan A b2b787292e52
wiki-write is a skill published in the GitHub repository Oshayr/LLM-Wiki (50 stars, last pushed 6mo ago), licensed MIT. It adds 90 tokens to every session and 906 once invoked, about $0.0004 per session on Opus 5.5. 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 skills, from other repositories
llm-wiki
Build and maintain an LLM-curated knowledge base from papers, articles, transcripts, notes and project findings. Ingest sources into linked Markdown, answer questions with citations, lint or upgrade a wiki, and preserve useful synthesis across sessions and agents. Also capture verified task experience, consolidate…
new
Start a new session — save summary to memory, then mark as reset so next message gets a fresh greeting. OpenClaw-compatible. Triggers on /new, /reset, /agent:new, "nueva sesión", "new session", "reset".
compact
Flush important session context to daily log (manual memory flush). Does NOT invoke native /compact. Triggers on /compact, /agent:compact, /flush, "guarda memoria", "flush".
alive:save
The human wants to checkpoint. Or: the stash has grown heavy — 5+ items, 30+ minutes, a natural pause in the work. The squirrel doesn't decide when to save. It surfaces the need and lets the human pull the trigger. Runs the full save protocol: confirms stash, writes log, updates state, generates projections…
alive:capture-context
Use when external content arrives in the session — emails, transcripts, screenshots, documents, files, or in-session research worth keeping. Also use when there's nothing obvious to capture — the skill checks 03Inbox/ for unrouted files and enters inbox scan mode. Stores raw content, routes to bundles, extracts tasks…
alive:session-history
Revive sessions (quick or heavy), browse, and search — 'what happened recently?', 'find the session where we discussed X', 'revive yesterday's session'. For single-session recall and multi-session browsing. If the human needs to merge multiple sessions into one working context or detect conflicts between parallel…