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-agent-memory-bridgegit 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-agent-memory-bridge)<a href="https://agentmods.dev/skills/po4yka/llm-wiki-skills/llm-wiki-agent-memory-bridge"><img src="https://agentmods.dev/badge/skills/po4yka/llm-wiki-skills/llm-wiki-agent-memory-bridge/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-agent-memory-bridge"><img src="https://agentmods.dev/badge/skills/po4yka/llm-wiki-skills/llm-wiki-agent-memory-bridge.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 | $0.00067 | $0.00767 |
| Opus 5 | $0.00034 | $0.00383 |
| Sonnet 5 | $0.00013 | $0.00153 |
| Haiku 4.5 | $0.00007 | $0.00077 |
Grade A, and why
llm-wiki-agent-memory-bridge 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LLM-Wiki Agent Memory Bridge
Goal
Separate durable domain knowledge from runtime/project memory so agents load the right context at the right time.
When to use
AGENTS.md/CLAUDE.mdhas grown large because domain facts were pasted into instructions instead of the wiki.- A wiki page holds procedural agent prompts that belong in a Skill, not domain knowledge.
- Agent memory (Auto Memory, Codex project memory) duplicates or has drifted from existing wiki pages.
- You need to decide where a new piece of knowledge belongs: Skill, instruction file, or wiki.
- Onboarding a new agent (Claude Code, Codex, Cursor, OpenCode) to a project and need to map its existing memory surfaces first.
Inputs
AGENTS.md,CLAUDE.md, project memory files, agent settings.- Existing wiki/vault.
- Target agents: Claude Code, Codex, Cursor, OpenCode, etc.
- Desired mode: audit, plan, or apply.
Procedure
1. Inventory memory surfaces
Find:
- instruction files;
- agent memory files;
- skills;
- wiki pages;
- query logs;
- project docs;
- hidden or generated memory directories.
2. Classify memory items
Use this routing:
| Content | Best home |
|---|---|
| stable procedures | Agent Skill |
| project conventions | AGENTS.md or CLAUDE.md pointer |
| domain facts | LLM-Wiki page with provenance |
| source-backed claims | wiki/sources, wiki/concepts, wiki/entities |
| user preferences | agent/user memory, not public wiki |
| temporary task state | current session or task log |
| sensitive facts | restricted wiki or local-only memory |
3. Detect bloat and drift
Flag:
- giant instruction files full of domain knowledge;
- skills containing volatile facts;
- agent memory duplicating wiki pages;
- wiki pages containing procedural prompts;
- missing pointers from instruction files to wiki index;
- volatile facts (pricing, release notes, maintenance status) embedded directly in a skill or instruction file instead of a wiki page whose claims get re-verified against fresh sources before reuse.
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 · 111 lines · 67 tokens per session scan A 576452f5895b
llm-wiki-agent-memory-bridge is a skill published in the GitHub repository po4yka/llm-wiki-skills (3 stars, last pushed 18d ago), licensed MIT. It adds 67 tokens to every session and 767 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
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…
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-export
Export a vault's wiki either as a single portable file (llms.txt or llms-full.txt per the llmstxt.org standard) or as an OKF knowledge bundle (Google's Open Knowledge Format v0.1 — a shareable directory of markdown files any AI agent can consume). Use when the user says "export my wiki", "make an llms.txt", "share my…
wiki-query
Answer a question using ONLY the existing wiki vault as the knowledge base — no web search, no general LLM knowledge. Reads hot.md first (cheap recent context), then catalog.md to navigate, then drills into specific pages, then optionally semantic-searches the wiki, and synthesizes an answer with citations. Use when…
wiki-fold
Roll up the wiki's journal.md entries into structured fold pages — like 2^k log compaction. Reads the last 2, 4, 8, 16... entries and writes a fold page that summarizes them by extractive summarization (no invention), with backlinks to children. Idempotent at the structural level — re-running with the same window…
wiki
Bootstrap or check a Karpathy-style "LLM wiki" structure inside an Obsidian vault — a self-maintaining knowledge base where pages reference each other and the LLM keeps it tidy. Sets up catalog.md (curated page catalog), journal.md (append-only operation history), hot.md (recent-context cache), and overview.md…