llm-wiki AGENTS.md

A catalogue of the tools and endpoints exposed by llm-wiki to AI agents, including search, document ingestion, context loading, and maintenance operations.

In plain words
What is it for?
It helps query the wiki with citations, add files, load recent context, save related research as a page, and run cleanup or repair jobs.
Why use it?
It tells an agent which calls to make at the start of a session, when answering questions, and when preserving research for later use.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/krishddd/llm-wiki/agents-md
Clone the repo
git clone --depth 1 https://github.com/krishddd/llm-wiki

Made for: Codex, OpenCode.

Per session 1,366 This file is loaded in full into every session.
When invoked 1,366 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.01366 $0.01366
Opus 5 $0.00683 $0.00683
Sonnet 5 $0.00273 $0.00273
Haiku 4.5 $0.00137 $0.00137

Measured 2d ago against content hash 765d59a39c6f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 2d 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.

AGENTS.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — LLM-Wiki agent surface

Agent-facing companion to CLAUDE.md. Lists the tools, resources, and conventions an MCP-aware agent (Claude Code, Cursor, Codex, etc.) must follow when driving this wiki. Loaded by llm_wiki/mcp_server.py.

Quick start for an agent

  1. Call context_start(days=7, top_pages=5) at the beginning of every new session. Returns recent episodic timeline + top accessed pages + open contradictions.
  2. To answer a user question: call query_wiki(question, top_k=5, save_back=true). The response carries numbered citations, per-claim confidences, and follow-up suggestions.
  3. After a chain of related queries, call session_crystallize(correlation_ids=[...]) to persist the exploration as one durable wiki page.
  4. To add a document: call ingest_file(path) with an absolute path on the host.
  5. Periodically (or when results feel stale) call run_admin_job("lint_autofix") or run_admin_job("decay_sweep") — same code paths as the in-process scheduler.

Tool catalogue (MCP)

Tool Purpose
query_wiki(question, top_k=5, save_back=true) Hybrid retrieval + reflective synthesis. Returns answer with [1] [2]-style citations, blocks, follow-ups, intent, retrieval quality.
ingest_file(path) Multi-format ingest (PDF/DOCX/HTML/PPTX/XLSX/CSV/MD/TXT). Confidence-gated write.
lint_wiki() Read-only health report.
list_entities(limit=50) Canonical entities by backlink count.
session_crystallize(correlation_ids, days=14) Distil an exploration thread into one wiki page.
context_start(days=7, top_pages=5) Session-start briefing.
run_admin_job(job_name) Manually trigger one of: decay_sweep, episodic_prune, promote_episodic, review_autopilot, lint_autofix, detect_procedures, build_topics, page_compaction, lint.

Resources (MCP)

Resource URI Content
wiki://index The current wiki/index.md (master catalogue, regenerated deterministically per ingest).

Read the full file on GitHub · 106 lines

Changes

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.

  1. 2d ago First seen · 106 lines · 1,366 tokens per session scan A 765d59a39c6f

Subscribe to this mod's changes

llm-wiki AGENTS.md is an instructions file published in the GitHub repository krishddd/llm-wiki (2 stars, last pushed 10d ago), licensed MIT. It adds 1,366 tokens to every session, about $0.0068 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.