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/kikocastro/markdown-mindmap/agents-mdgit clone --depth 1 https://github.com/kikocastro/markdown-mindmapWhat 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 | $0.01276 | $0.01276 |
| Opus 5 | $0.00638 | $0.00638 |
| Sonnet 5 | $0.00255 | $0.00255 |
| Haiku 4.5 | $0.00128 | $0.00128 |
Grade A, and why
markdown-mindmap 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.
How it starts
The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent guide
Canonical instructions for coding agents in this repo. CLAUDE.md and GEMINI.md are symlinks to this file, so every tool reads one source.
What this is
Leveled left-to-right mind maps from note frontmatter links, with two adapters over one shared core: an Obsidian plugin and a VS Code extension. One ```mindmap YAML block per map (see README.md). A block renders as one of three view types (view: map | gantt | kanban): the same collected + filtered tree laid out as a tree of cards, a gantt (bars by gantt.start/gantt.end, milestone diamonds), or a kanban board (columns by kanban.groupBy). Filters/search/collapse apply before layout, so they work in every view. A second block type, ```causalmap, renders causal-loop diagrams (systems-thinking graphs with automatic cycle detection) — Obsidian only for now.
Architecture
src/core/— pure core. No host coupling. Modules:config(types + defaults),helpers,collect,edges,visibility,layout-tree,layout-gantt,layout-kanban,views,render-model(buildRenderModel-> the serializableRenderModelboth adapters draw; dispatches on the view type),export(HTML/Excalidraw export builders). All unit-tested. Shared by both adapters.src/graph.ts— re-exporting barrel oversrc/core/; every import path goes through it.src/causal.ts— pure causal-map core. Imports only fromgraph.ts. Signed-edge collection, cycle detection, loop polarity, force-directed layout. Same rules as the core: host-free, 100% covered.src/render/— shared SVG renderer (renderer.tsdraws aRenderModelinto an injected document/SVG root for all three views;panzoom.tsowns pan/zoom/fit). The only DOM code outside the adapters; coverage-excluded like them, but lint-covered and bundled into both builds.src/obsidian/— Obsidian adapter.main.ts(```mindmapblocks),causal.ts(```causalmapblocks),modals.ts(prompt/confirm/help/note dialogs) — the only files that importobsidian— plussvg.ts, a host-free element helper. Owns host I/O (vault read, resolver, code-block processor, YAML write-back), toolbar/state wiring, and exports. Buildsmain.js.src/vscode/— VS Code adapter.extension.ts(host: reads workspace markdown, runsbuildRenderModel, posts theRenderModel),webview.ts(bootstrap: shared renderer + pan/zoom + click-to-open). Buildsdist/extension.js+dist/webview.js.styles.css— Obsidian theming via CSS variables. (VS Code styling is inline in the webview HTML shell, using--vscode-*vars.)test/— vitest, exercising the core through plainNoteLikedata (host-agnostic).
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 · 50 lines · 1,276 tokens per session scan A f857e4b700ec
markdown-mindmap AGENTS.md is an instructions file published in the GitHub repository kikocastro/markdown-mindmap (11 stars, last pushed 3d ago), licensed MIT. It adds 1,276 tokens to every session, about $0.0064 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.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.