my-wiki AGENTS.md

Repository guidance for My Wiki, an application that captures, organises, searches, and displays personal knowledge. It also explains the separate user vault, the command-line workflow, and the optional agent playbook.

In plain words
What is it for?
Use it when changing knowledge capture, searches, maintenance workflows, evidence records, visual knowledge maps, sharing, the dashboard, deployment, or related tests.
Why use it?
It prevents an agent from confusing the application code with a user's knowledge vault and defines the project's terms and boundaries.

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/nimachu/my-wiki/agents-md
Clone the repo
git clone --depth 1 https://github.com/NimaChu/my-wiki

Made for: Codex, OpenCode.

Per session 617 This file is loaded in full into every session.
When invoked 617 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 $0.00617 $0.00617
Opus 5 $0.00309 $0.00309
Sonnet 5 $0.00123 $0.00123
Haiku 4.5 $0.00062 $0.00062

Measured 3d ago against content hash 21b088cfc98c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

my-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 3d 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 · 37 lines

How it starts

The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.

My Wiki Agent Project

This repository is the runnable My Wiki application. It is neither a knowledge vault nor merely an installed Agent Skill.

Project Map

  • scripts/ contains the CLI and knowledge-maintenance implementation.
  • assets/dashboard/ contains the web application and local service.
  • deploy/ contains standalone deployment options.
  • tests/ covers application and workflow contracts.
  • my-wiki-skill/SKILL.md is the canonical Agent playbook for capture, query, maintenance, evidence, galaxies, sharing, and Dashboard operations.
  • The user's vault is external to this repository and owns root index.md/log.md, concepts/, references/, templates, and .my-wiki/ runtime state.

The project can run directly with npm run wiki -- <command> and does not require a globally installed Skill. The adapter under my-wiki-skill/ is optional for Agents working from other workspaces.

Knowledge Model

Use the native OKF terms in explanations and new documentation: a durable knowledge page is a Concept, captured evidence is a Reference, and the preserved binary or webpage snapshot is an original. My Wiki visualizes Concepts as concept planets grouped into knowledge galaxies. Historical command names, internal variables, and package fields may still contain wiki, raw, or universe for compatibility; do not infer the old wiki/ or raw/ directories from those identifiers.

Route Requests

Classify the request before acting:

  1. Knowledge operation: For capturing sources, answering knowledge questions, searching the vault, maintaining knowledge, inspecting evidence, managing galaxies, importing/exporting, or opening the Dashboard, read my-wiki-skill/SKILL.md first and follow the relevant reference it names. Ordinary questions about concepts, people, products, methods, events, companies, or named projects belong to this route unless the user explicitly asks about repository code.
  2. Project development: For implementation, architecture, tests, bugs, CLI behavior, frontend behavior, or deployment code, work from this repository and preserve its existing engineering patterns.
  3. Installation or bootstrap: Enter setup only when the user asks to install/configure My Wiki or when the operational playbook reports that the project registration or vault is missing. Follow the README and Skill guidance; do not repeat initialization during normal use.
  4. Repository publishing: Code may be committed and pushed when requested. Vault knowledge, originals, exports, credentials, and local runtime state must never enter this repository.

Read the full file on GitHub · 37 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. 3d ago First seen · 37 lines · 617 tokens per session scan A 21b088cfc98c

Subscribe to this mod's changes

my-wiki AGENTS.md is an instructions file published in the GitHub repository NimaChu/my-wiki (123 stars, last pushed 3d ago), licensed MIT. It adds 617 tokens to every session, about $0.0031 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.