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/aiwork4me/open-llm-wiki/agents-mdgit clone --depth 1 https://github.com/AIwork4me/open-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/instructions/aiwork4me/open-llm-wiki/agents-md)<a href="https://agentmods.dev/instructions/aiwork4me/open-llm-wiki/agents-md"><img src="https://agentmods.dev/badge/instructions/aiwork4me/open-llm-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 5.1 | $0.00748 | $0.00748 |
| Opus 5 | $0.00374 | $0.00374 |
| Sonnet 5 | $0.00150 | $0.00150 |
| Haiku 4.5 | $0.00075 | $0.00075 |
Grade A, and why
open-llm-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 5d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Contributor guide for humans and AI agents working on open-llm-wiki.
Project Scope
open-llm-wiki is a Claude Code skill bundle plus a small wiki schema. The core
product is the behavior of the three skills in skills/:
wiki-ingest: one-source ingest with independent QAquery-writeback: read-first synthesis with approved writebackwiki-lint: report-first health checks with optional approved fixes
Hard Rules
- Keep every
skills/<name>/SKILL.mdfolder name aligned with its frontmattername. - Use
uv sync --devanduv run ...for Python and validator commands. Do not install project dependencies into the global Python environment. - Validate skills with
uv run python -m skills_ref.cli validate. - Do not add unsupported frontmatter fields. Use
metadatafor versioning. - Basic use must not require API keys. Cloud OCR is optional and must be disclosed because document content may leave the local machine.
- Do not commit
.env, API tokens, generated parser output, or private source documents. - Prefer runtime scripts for repeatable operations:
wiki_init.py,pdf_corpus_report.py,pdf_corpus_to_markdown.py,pdf_to_markdown.py,wiki_ingest_corpus.py,wiki_claims.py,wiki_normalize_metrics.py,wiki_semantic_qa.py,wiki_contradictions.py,wiki_science_review.py,wiki_discover_sources.py,wiki_queue.py,wiki_concept_revision.py,wiki_grow.py,wiki_lint.py,wiki_search.py,wiki_writeback.py, andwiki_eval.py. raw/files are immutable evidence.- QA reports and contradiction reports are append-only.
- Query writeback and lint are read-only by default.
- No secrets, private papers, personal notes, or API keys belong in the repo.
Repo Map
open-llm-wiki/
|-- README.md
|-- README.zh.md
|-- QUICKSTART.md
|-- SCHEMA.md
|-- AGENTS.md
|-- skills/
| |-- wiki-ingest/
| |-- query-writeback/
| `-- wiki-lint/
|-- templates/
|-- examples/
|-- scripts/
|-- .github/workflows/
`-- assets/
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.
- 5d ago First seen · 90 lines · 748 tokens per session scan A 89ef3be7f82a
open-llm-wiki AGENTS.md is an instructions file published in the GitHub repository AIwork4me/open-llm-wiki (2 stars, last pushed 3mo ago), licensed MIT. It adds 748 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
Instructions for vbarsoum1/llm-wiki-compiler, covering klore — llm knowledge compiler, available commands, when to use and prerequisites.
llm-wiki-compiler copilot-instructions.md
Instructions for vbarsoum1/llm-wiki-compiler, covering klore — llm knowledge compiler, available commands, when to use and prerequisites.
llm-wiki-compiler CLAUDE.md
Instructions for vbarsoum1/llm-wiki-compiler, covering klore — llm knowledge compiler and skill routing.
llm-wiki-compiler GEMINI.md
Instructions for vbarsoum1/llm-wiki-compiler, covering klore — llm knowledge compiler, available commands, when to use and prerequisites.
llm-wiki-agent AGENTS.md
AGENTS.md instructions for SamurAIGPT/llm-wiki-agent, covering llm wiki agent — schema & workflow instructions, how to use, directory layout, page format and ingest workflow.
llm-wiki-agent CLAUDE.md
Claude Code instructions for SamurAIGPT/llm-wiki-agent, covering llm wiki agent — schema & workflow instructions, slash commands (claude code), directory layout, page format and ingest workflow.