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-adr-memorygit 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-adr-memory)<a href="https://agentmods.dev/skills/po4yka/llm-wiki-skills/llm-wiki-adr-memory"><img src="https://agentmods.dev/badge/skills/po4yka/llm-wiki-skills/llm-wiki-adr-memory/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-adr-memory"><img src="https://agentmods.dev/badge/skills/po4yka/llm-wiki-skills/llm-wiki-adr-memory.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 | $0.00058 | $0.00569 |
| Opus 5 | $0.00029 | $0.00284 |
| Sonnet 5 | $0.00012 | $0.00114 |
| Haiku 4.5 | $0.00006 | $0.00057 |
Grade A, and why
llm-wiki-adr-memory 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LLM-Wiki ADR Memory
Goal
Make architectural and product decisions traceable, searchable and durable.
When to use
- Someone asks why a technical or product decision was made and no clear record exists.
- A PR, issue, or discussion thread contains decision rationale that should be distilled into a durable ADR.
- An existing ADR needs to be linked into the wiki or checked against newer commits/docs for stale assumptions.
- A subsystem lacks decision provenance and the user wants it recovered from history before further changes land.
Inputs
- Existing ADRs, docs, PRs, issues, discussions or commit history.
- Target decision or subsystem.
- Desired mode: recover, create draft ADR, update wiki, or answer a question.
Procedure
1. Identify decision scope
Clarify:
- decision title;
- affected system/domain;
- approximate time window;
- stakeholders if known;
- current pain point.
2. Gather evidence
Search:
- ADR files;
- PR descriptions and review threads;
- issues and discussions;
- commit messages;
- architecture docs;
- wiki pages;
- meeting notes if available.
3. Build decision timeline
Extract:
- context;
- options considered;
- constraints;
- trade-offs;
- final decision;
- consequences;
- assumptions that may now be stale.
4. Create or update decision page
Recommended structure:
# Decision: <title>
## Status
## Context
## Options considered
## Decision
## Consequences
## Evidence
## Stale assumptions
## Follow-ups
Use status: draft unless an owner approves.
5. Link into wiki
Connect decision pages to concepts, entities, repo docs and relevant source pages. Add to wiki/index.md if important.
Output
## Decision memory summary
## Evidence reviewed
## Timeline
## Draft ADR or wiki page
## Unresolved questions
## Recommended owners
Safety gates
- Do not invent rationale when evidence is missing.
- Do not treat inferred motivation as extracted fact.
- Do not rewrite official ADRs without review.
- Do not expose private discussion excerpts unnecessarily.
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 · 119 lines · 58 tokens per session scan A aada58880ded
llm-wiki-adr-memory is a skill published in the GitHub repository po4yka/llm-wiki-skills (3 stars, last pushed 19d ago), licensed MIT. It adds 58 tokens to every session and 569 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…