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/shailesh200/prism/claude-mdgit clone --depth 1 https://github.com/Shailesh200/prismWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/shailesh200/prism/claude-md)<a href="https://agentmods.dev/instructions/shailesh200/prism/claude-md"><img src="https://agentmods.dev/badge/instructions/shailesh200/prism/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00522 | $0.00522 |
| Opus 5 | $0.00261 | $0.00261 |
| Sonnet 5 | $0.00104 | $0.00104 |
| Haiku 4.5 | $0.00052 | $0.00052 |
Grade A, and why
prism CLAUDE.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 4d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Claude / Agent Notes for Prism
Companion to
AGENTS.md. Follow both.
Project
Prism — local-first Software Intelligence Engine (maps, graphs, impact, health) exposed via Core, MCP, CLI, and IDE extensions.
Before writing code
- Confirm Master Plan status is APPROVED (
plans/00_MASTER_DEVELOPMENT_PLAN.md). - Confirm M-000 Architecture Documentation is Verified (HLD/LLD/tech docs under
plans/architecture/). - Confirm exactly one milestone is
In Progressinplans/PROGRESS.md. - Work only on
milestone/M-XXX-…branch created from latestmain. - Implement only that milestone’s In Scope items.
First code milestone is M-001 (after M-000).
Do not
- Develop on
main - Stack milestone branches
- Create git commits before the owner explicitly approves (keep work in the working tree until then)
- Push remotes unless the human owner explicitly requests it
- Bypass
@repo-prism/corefrom MCP/CLI/extensions - Add cloud/network dependencies to Core analysis paths
- Expand milestone scope silently
Preferred workflow
Read milestone doc → implement (no commits) → bun run verify:milestone → fix → request owner review → owner approves → commit on milestone branch → owner approves merge → merge locally to main → mark Verified → share short “what changed” snippet with owner → next branch from main
Packages (mental model)
| Package | Role |
|---|---|
| shared | contracts |
| analyzer / indexer / graph-engine | engine internals |
| intelligence / impact / navigation / repository-map | domain engines |
| dispatch | jobs, memories, OAuth drivers, local workers |
| dispatch-auth | Prism Auth OAuth broker (website /oauth/*) |
| core | public SDK (analysis) |
| mcp-server / cli / vscode-extension / cursor-extension / ui | surfaces |
MCP
Intelligence tools call Core and return JSON-serializable DTOs from @repo-prism/shared.
Dispatch tools call @repo-prism/dispatch on a second registration path and must
not go through session.ready() / the Core Result wrapper (ADR-0035).
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.
- 4d ago First seen · 55 lines · 522 tokens per session scan A 4cf34b51230f
prism CLAUDE.md is an instructions file published in the GitHub repository Shailesh200/prism (1 stars, last pushed 2d ago), licensed MIT. It adds 522 tokens to every session, about $0.0026 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 2026-08-31.
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.