What is Kompl AGENTS.md?

An operating guide for Kompl, a tool that turns saved links, files, and bookmarks into a connected personal wiki. It also sets safety rules for Docker commands that could erase the wiki.

Use it when installing, updating, backing up, configuring, or safely operating Kompl.

It gives an agent the project’s operating instructions and helps prevent accidental loss of the wiki’s stored data.

Kompl AGENTS.md — Instructions file by tuirk

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/tuirk/kompl/agents-md

Clone the repo

git clone --depth 1 https://github.com/tuirk/Kompl

Made for: Codex, OpenCode.

Per session 1,091 This file is loaded in full into every session.

When invoked 1,091 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.

Model	Per session	Once invoked
Fable 5	$0.01091	$0.01091
Opus 5	$0.00545	$0.00545
Sonnet 5	$0.00218	$0.00218
Haiku 4.5	$0.00109	$0.00109

Measured 2d ago against content hash f248063befea, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Kompl 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 · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Kompl operator guide

For AI agents helping a user install, update, and use Kompl.

Use README.md as the source of truth for prerequisites, install, day-to-day commands, updating, backup, MCP setup, data handling, security, and known limitations. Install path: projectDir in ~/.kompl/config.json.

What is Kompl?

Kompl is a compounding LLM-wiki: it turns saved links, files, and bookmarks into an interlinked wiki when each source arrives, not when you ask later. For the full product description, see README § What is Kompl?.

Agent rules — wiki safety (read before any Docker command)

The user's wiki (SQLite DB, page files, vectors) lives on the Docker named volume kompl-data. You can destroy their entire wiki with one flag. Treat that as irreversible until they restore from a .kompl.zip.

NEVER without explicit user confirmation

Do not run, suggest, or script any of the following unless the user has explicitly confirmed in this conversation that they accept losing their wiki (or are on a fresh throwaway install with nothing to lose):

Command / action	Why it wipes data
`docker compose down -v`	`-v` deletes named volumes including `kompl-data`
`docker volume rm …` / deleting `kompl-data` in Docker Desktop	Direct volume deletion
`bash scripts/integration-test.sh`	Runs `docker compose down -v` by design
Re-installing into a new clone and removing old volumes	Orphaned or replaced `kompl-data`

If the user has not clearly said they want a full wipe, stop and ask. Do not imply these are routine cleanup steps.

If a destructive action is going to happen anyway

When the user has explicitly ordered a wipe or you must run a destructive command for a stated reason:

Run kompl backup first — no exceptions.
Confirm the backup file exists (default: ~/.kompl/backups/kompl-backup.kompl.zip, or --output path they chose).
Tell the user where the backup is before running the destructive command.
Only then proceed.

Read the full file on GitHub · 79 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.

2d ago First seen · 79 lines · 1,091 tokens per session scan A f248063befea

Subscribe to this mod's changes

Kompl AGENTS.md is an instructions file published in the GitHub repository tuirk/Kompl (76 stars, last pushed 8d ago), licensed Apache-2.0. It adds 1,091 tokens to every session, about $0.0055 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 2026-08-30.

Data and AI DevOps and cloud LLM knowledge-management llm-wiki mcp obsidian-alternative personal-knowledge-management

obsidian-llm-wiki AGENTS.md

Instructions for green-dalii/obsidian-llm-wiki, covering llm wiki plugin project development standards, 🛡️ six-gate quality closure, gate 1: five-gate automated, gate 2: no side effects and gate 3: no breaking changes.

green-dalii/obsidian-llm-wiki · 7,700 tokens

obsidian-llm-wiki CLAUDE.md

Instructions for green-dalii/obsidian-llm-wiki, a project described as: Karpathy's LLM Wiki implementation plugin for Obsidian - turns notes and PDFs into a linked, LLM-powered knowledge base with entity pages, concept pages, graph-powered Q&A, and local-first privacy.

green-dalii/obsidian-llm-wiki · 234 tokens

Kompl AGENTS.md