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/kitlangton/merman/agents-mdgit clone --depth 1 https://github.com/kitlangton/mermanWhat 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 | $0.02164 | $0.02164 |
| Opus 5 | $0.01082 | $0.01082 |
| Sonnet 5 | $0.00433 | $0.00433 |
| Haiku 4.5 | $0.00216 | $0.00216 |
Grade A, and why
merman 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agents Guide
Orientation for AI assistants and humans dropping into this repo. Keep this in sync with the actual layout — tests and consumers depend on the public surface described here.
What this package is
merman parses a small Mermaid-flavored DSL and renders three
diagram families to the terminal:
- Flowchart — boxed nodes, routed edges, subgraphs, animated pulses
- State — composite states, nested regions, active-transition highlighting
- Sequence — participants, messages, notes, fragments, activations
Each family has three rendering paths:
- Plain text (
renderXDiagram) — uncolored grid, ideal for tests - ANSI (
renderXDiagramAnsi) — colored string for direct terminal print - OpenTUI Renderable (
XDiagramRenderable) — live, themeable, interactive
@opentui/core is a peer dependency. We do not own renderable primitives,
the CLI loop, or styled text — we own diagram parsing, layout, routing, and
the diagram-specific rendering pipeline.
Source layout
src/
├── index.ts # Single public entrypoint (re-exports flowchart/state/sequence)
├── cli/ # Bun CLI output and source-comment transforms
│ ├── main.ts # Args, diagram dispatch, terminal/doc-comment output
│ ├── doc-comment.ts # TypeScript /** ... */ formatting
│ └── replace.ts # Inline Mermaid fences -> rendered TS or Markdown lines
├── flowchart/ # Flowchart pipeline
│ ├── parser.ts # Mermaid string -> FlowchartDiagram
│ ├── layout.ts # FlowchartDiagram -> placed bounds/routes
│ ├── routing.ts # Edge routing on the diagram grid
│ ├── labels.ts # Edge label placement
│ ├── render.ts # Plain/ANSI rendering facade
│ ├── drawing.ts # FlowchartDiagram -> styled diagram grid
│ ├── style.ts # Themes, color keys
│ ├── options.ts # Public option types
│ ├── renderable.ts # FlowchartDiagramRenderable (OpenTUI)
│ ├── types.ts # Public data model
│ └── index.ts # Public re-exports for this family
├── state/ # State diagrams
│ ├── parser.ts # Mermaid string -> StateDiagram
│ ├── visible-model.ts # StateDiagram -> visible transitions/states for drawing
│ ├── layout.ts # StateDiagram -> placed bounds
│ ├── routing.ts # Visible State transitions -> route kinds for drawing
│ ├── drawing.ts # StateDiagram -> styled diagram grid
│ ├── style.ts # Themes, colors, pulse style ramps
│ ├── render-grid.ts # Grid -> string / ANSI / StyledText
│ ├── diagram.ts # Plain/ANSI rendering facade
│ ├── renderable.ts # StateDiagramRenderable (OpenTUI)
│ ├── options.ts # Defaults and option normalization
│ ├── types.ts # Public data model and options
│ └── index.ts # Public re-exports for this family
├── sequence/ # Sequence diagrams
│ ├── parser.ts # Mermaid string -> SequenceDiagram
│ ├── placement.ts # SequenceDiagram -> static participant/step placement plan
│ ├── drawing.ts # SequenceDiagram -> styled diagram grid
│ ├── style.ts # Themes, colors, pulse style ramps
│ ├── render-grid.ts # Grid -> string / ANSI / StyledText
│ ├── diagram.ts # Plain/ANSI rendering facade
│ ├── renderable.ts # SequenceDiagramRenderable (OpenTUI)
│ ├── options.ts # Defaults and option normalization
│ ├── types.ts # Public data model and options
│ └── index.ts # Public re-exports for this family
├── core/ # Package-internal primitives, NOT publicly exported
│ ├── canvas.ts # DiagramCanvas: 2D char grid abstraction
│ ├── geometry.ts # Boxes, points, intersection helpers
│ ├── drawing.ts # Box / line drawing primitives
│ ├── render-grid.ts # Grid -> string / ANSI / StyledText
│ ├── text.ts # Width-aware text helpers (string-width)
│ ├── text-lines.ts # Wrapping / line splitting
│ ├── mermaid.ts # Shared Mermaid line tokenization
│ ├── adapter/ # OpenTUI color parsing and renderable invalidation pipeline
│ ├── animation/ # Pulse animation core (frame counter, cell styling)
│ ├── color/ # Color ramps, theme maps, fade levels
│ └── terminal/ # ANSI escape helpers
└── test/ # Cross-cutting integrity tests + shared test helpers
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 · 181 lines · 2,164 tokens per session scan A 4a6b8cee4c52
merman AGENTS.md is an instructions file published in the GitHub repository kitlangton/merman (47 stars, last pushed 1mo ago), licensed MIT. It adds 2,164 tokens to every session, about $0.0108 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
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.
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).
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.