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 instructions/xccelephant/agent-wiki/agents-mdgit clone --depth 1 https://github.com/xccElephant/agent-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/instructions/xccelephant/agent-wiki/agents-md)<a href="https://agentmods.dev/instructions/xccelephant/agent-wiki/agents-md"><img src="https://agentmods.dev/badge/instructions/xccelephant/agent-wiki/agents-md.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 | $0.00739 | $0.00739 |
| Opus 5 | $0.00369 | $0.00369 |
| Sonnet 5 | $0.00148 | $0.00148 |
| Haiku 4.5 | $0.00074 | $0.00074 |
Grade A, and why
agent-wiki AGENTS.md 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 4d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- agent-wiki CLAUDE.md — 91% identical, 3 lines differ
How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LLM Wiki Agent Guide
This repository is a template for a persistent, LLM-maintained wiki built on top of raw sources.
This file is intended for Codex-style agents and other tools that read AGENTS.md. Keep it aligned with CLAUDE.md when changing the workflow.
Directory Roles
raw/is the immutable source layer.raw/articles/stores original article notes, clips, and imported markdown sources.raw/assets/stores local images and attachments.wiki/source-notes/stores one derived note per source.wiki/entities/stores concrete entities such as people, orgs, products, tools, papers, and datasets.wiki/concepts/stores methods, definitions, and recurring ideas.wiki/synthesis/stores comparisons, theses, timelines, and multi-source analyses.wiki/index.mdis the main navigation page.logs/log.mdis the append-only operational record.schemas/stores structural guidance and workflow docs.
Core Rules
- Treat files in
raw/as source snapshots. Do not silently rewrite them to fix conclusions. - Put interpretation, corrections, and synthesis in
wiki/. - Read
wiki/index.md,logs/log.md, and relevant wiki pages before diving into raw sources. - Use
[[wikilinks]]for internal vault references and Markdown links only for external URLs. - For important claims, point to the relevant
wiki/source-notes/page and, when useful, the underlying raw source.
Claim Types
Separate these categories whenever possible:
Fact: directly supported by a source.Inference: synthesis or interpretation drawn from sources.Dispute: conflicting claims or unresolved contradictions.Open Question: gaps, next steps, or hypotheses that still need validation.
Ingest Workflow
- Determine which sources to ingest.
- If the user explicitly names source files, use those files only.
- Otherwise, discover candidate sources in
raw/articles/orraw/assets/and decide which ones are new or need updating. - Match each selected source against existing notes in
wiki/source-notes/. - Treat a source as already ingested when a corresponding source note clearly points back to the raw file, ideally through
raw_pathor an equivalent explicit reference. - Prefer updating an existing source note instead of creating a duplicate when the mapping is clear.
- Create or update the matching note in
wiki/source-notes/. - Extract summary, key claims, notable evidence, related entities, related concepts, disputes, and open questions.
- Update affected pages in
wiki/entities/,wiki/concepts/, andwiki/synthesis/. - Refresh
wiki/index.mdwhen new durable pages are added. - Append an entry to
logs/log.md. - When multiple or auto-discovered sources were processed, append a concise batch summary and run a light lint pass on the touched wiki pages.
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.
- 4d ago First seen · 68 lines · 739 tokens per session scan A 9d2aaad3fab9
agent-wiki AGENTS.md is an instructions file published in the GitHub repository xccElephant/agent-wiki (4 stars, last pushed 4mo ago), licensed MIT. It adds 739 tokens to every session, about $0.0037 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 instructions, from other repositories
llm-wiki-compiler AGENTS.md
AGENTS.md instructions for atomicstrata/llm-wiki-compiler, covering llmwiki, development guidelines, code style & standards, clean code rules and comments and documentation.
abap_wiki AGENTS.md
AGENTS.md instructions for Gixsy95/abap_wiki, covering agents.md - abapwiki operating contract, 1. identity and mission, 2. language, 3. architecture: the two planes and 4. inviolable rules.
hippocampus CLAUDE.md
Instructions for sturlese/hippocampus, covering layout, frontmatter schema, conventions, answering questions from the vault (read order) and contradictions.
llm-wiki AGENTS.md
Instructions for cobusgreyling/llm-wiki, covering llm wiki agent instructions, architecture, page types, special files and log entry format.
hippocampus AGENTS.md
Instructions for sturlese/hippocampus: Read and follow CLAUDE.md in the repository root completely before doing any work. It is the canonical project contract, written for Claude Code as the native host; its vault rules and workflows apply unchanged to Codex.
LLM-Wiki AGENTS.md
Instructions for VectorPeak/LLM-Wiki, covering obsidian second brain - codex cli operating manual, how to operate, command routing tables (grouped by category), wiki layer - simplified knowledge operations and vault - daily writing, capture, find.