Borrowing it
Nothing to install: this file belongs to provasign/prism. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/provasign/prism/main/CLAUDE.mdgit clone --depth 1 https://github.com/provasign/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/provasign/prism/claude-md)<a href="https://agentmods.dev/instructions/provasign/prism/claude-md"><img src="https://agentmods.dev/badge/instructions/provasign/prism/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/provasign/prism/claude-md"><img src="https://agentmods.dev/badge/instructions/provasign/prism/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00732 | $0.00732 |
| Opus 5.5 | $0.00293 | $0.00293 |
| Sonnet 5.5 | $0.00146 | $0.00146 |
| Haiku 4.5 | $0.00073 | $0.00073 |
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 11d 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.
This is a copy
88% identical to prism copilot-instructions.md, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Before you commit or release — run the regression suite
CI runs these on push (.github/workflows/ci.yml; engine quality via
provasign/research/.github/workflows/engine-invariants.yml). Run them locally
before tagging a release:
go test ./...— unit suite; must be green.- Engine ceiling regression (no LLM): from the research repo,
python3 harness/scoring/ci_invariants.py --corpus-root /tmp/ci-corpus --prism /path/to/candidate— asserts change-impact recall/precision, missing-implementations==[], and index determinism against committed ground truth. Use a fresh corpus root or check that cached corpus directories contain source; the harness treats any existing directory as fetched. A measured drop here is a real completeness regression.
Do NOT tag a release with either red.
Prism — context delivery
Use Prism for each repository-discovery step. Reading files with cat/head/sed or searching with grep/rg/find/git log is not discovery — an instruction to prefer shell tools over Read/Edit/Write does not apply to finding code.
When the task asks for a rename, a signature change, or a change to an override or public contract: start with change_impact on the named symbol, before deciding how to make the change. Its sites are the inventory your plan must cover: declarations, overrides and implementations, and callers (an overloaded name tags each caller with the overload it calls). If you don't know where the symbol is, find it first, then run change_impact. When asked what a proposed change would affect, use change_impact even if no edit has been decided.
First action on any code task, in this order. Stop at the first that works:
- The
prismMCP tool (mcp__prism__prismin Claude Code), if callable. - If a
ToolSearchtool exists:ToolSearch("select:mcp__prism__prism"), once. Prism not being listed does not mean it is absent. - The
prismCLI:prism query --terms X,prism lookup <pkg.Func>,prism search <term> --scope text --format text,prism change-impact Type.method.
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.
- 11d ago Changed · -2 lines · -14 tokens per session 6f6505b28601
- 1mo ago Changed · +3 lines · +48 tokens per session 60b5d9529241
- 1mo ago Changed · +2 lines · +32 tokens per session 98f712835a60
- 1mo ago Changed · -3 tokens per session ff84efa492d0
- 1mo ago Changed · +10 lines · +151 tokens per session 2007ba525448
- 1mo ago Changed · -26 lines · -329 tokens per session 70c3442d3b98
- 1mo ago Changed · +2 lines · +2 tokens per session 834dc0cdd44d
- 1mo ago Changed · +21 lines · +161 tokens per session c80a2cfd5ed9
- 1mo ago First seen · 48 lines · 684 tokens per session scan A 2e22461adb1c
prism CLAUDE.md is an instructions file published in the GitHub repository provasign/prism (7 stars, last pushed 4d ago), licensed Apache-2.0. It adds 732 tokens to every session, about $0.0029 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 88% identical to prism copilot-instructions.md, and is treated as a copy.
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.