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/microsoft/msagljs/copilot-instructionsgit clone --depth 1 https://github.com/microsoft/msagljsWhat 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 | $0.00924 | $0.00924 |
| Opus 5 | $0.00462 | $0.00462 |
| Sonnet 5 | $0.00185 | $0.00185 |
| Haiku 4.5 | $0.00092 | $0.00092 |
Grade A, and why
msagljs copilot-instructions.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.
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot Instructions for msagl-js
Project Overview
msagl-js is a JavaScript/TypeScript implementation of Microsoft's Automatic Graph Layout (MSAGL) algorithms. It computes node positions and edge routes for graph visualization.
Build, Test, and Lint
yarn build # Build all modules (lerna + tsc + esbuild bundles)
yarn test # Run all tests (Jest with ts-jest)
yarn typecheck # Type-check without emitting (tsc --noEmit)
yarn eslint # Lint modules/core/src
yarn prettier # Format modules/core/src
Run a single test file:
npx jest --testPathPattern="graph.spec"
Run examples locally:
cd examples/svg-renderer && npm run start
cd examples/webgl-renderer && npm run start
Architecture
This is a Yarn workspaces + Lerna monorepo with six @msagl/* packages under modules/:
@msagl/core → Graph data model, layout algorithms, math, routing
@msagl/drawing → Visual attributes (colors, shapes, styles) for nodes/edges
@msagl/parser → DOT and JSON graph format parsers
@msagl/renderer-common → Shared renderer utilities (text measurement, etc.)
@msagl/renderer-svg → SVG renderer (uses panzoom)
@msagl/renderer-webgl → WebGL renderer (uses deck.gl)
Dependency flow (each arrow means "depends on"):
core ← drawing ← parser ← renderer-common ← renderer-svg
← renderer-webgl
core has zero internal dependencies. All other modules depend on core.
Core Data Model (@msagl/core)
GraphextendsNode— a graph is also a node, enabling nested/clustered subgraphsNodeextendsEntity— has anidstring andinEdges/outEdges/selfEdgessetsEdgeextendsEntity— connectssourceandtargetnodes; self-registers in node edge sets on constructionGeomGraph/GeomNode/GeomEdge— geometry layer counterparts that store computed positions, curves, and bounding boxes- Layout and geometry are separate from the structural graph —
Graph/Node/Edgehold structure,Geom*objects hold layout results
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.
- 3d ago First seen · 78 lines · 924 tokens per session scan A 7e827c0d187c
msagljs copilot-instructions.md is an instructions file published in the GitHub repository microsoft/msagljs (175 stars, last pushed 14d ago), licensed MIT. It adds 924 tokens to every session, about $0.0046 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
graphiti CLAUDE.md
Instructions for getzep/graphiti, covering claude.md, project overview, development commands, main development commands (run from project root) and install dependencies.
hugegraph AGENTS.md
AGENTS.md instructions for apache/hugegraph, covering agents.md, stack & modules, code search anchors, build and all modules.
tinkerpop AGENTS.md
Instructions for apache/tinkerpop, covering agents.md, primary guidance: agent skills, planning and memory: beads, canonical documentation and licensing and provenance.
graphiti AGENTS.md
Instructions for getzep/graphiti, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
pygraphistry AGENTS.md
AGENTS.md instructions for graphistry/pygraphistry, covering agents.md, skill locations, platform path conventions, canonical -> tool-expected path and claude path to shared skills.
pygraphistry CLAUDE.md
Claude Code instructions for graphistry/pygraphistry: See AGENTS.md for repository AI guidance.