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/AGENTS.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/agents-md)<a href="https://agentmods.dev/instructions/provasign/prism/agents-md"><img src="https://agentmods.dev/badge/instructions/provasign/prism/agents-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/agents-md"><img src="https://agentmods.dev/badge/instructions/provasign/prism/agents-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 | $0.00638 | $0.00638 |
| Opus 5.5 | $0.00255 | $0.00255 |
| Sonnet 5.5 | $0.00128 | $0.00128 |
| Haiku 4.5 | $0.00064 | $0.00064 |
Grade A, and why
prism 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 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
100% 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Development workflow
Do not commit or push any change until the user explicitly reviews the work and approves the commit and push. Completing implementation or validation is not approval. Keep changes uncommitted while awaiting that approval.
All changes must be made, committed, and pushed directly on main. Do not
create or use feature, task, cleanup, or reconciliation branches for repository
changes. Before editing or committing, confirm the active branch is main.
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.
For each discovery step, pick the Prism op: known symbol -> lookup unknown location/text -> search known file/range -> read callers/related -> query pre-edit sites -> change_impact tests naming known symbols -> search with test path/glob, files_only indirect tests -> query
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 052a20c91fdb
- 1mo ago Changed · +3 lines · +48 tokens per session 086abfa7c455
- 1mo ago Changed · +2 lines · +32 tokens per session d40939e428f3
- 1mo ago Changed · -3 tokens per session 34d6267f87b7
- 1mo ago Changed · +8 lines · +110 tokens per session f10f9f23bb9c
- 1mo ago Changed · -22 lines · -287 tokens per session 37e5dbc93c51
- 1mo ago Changed · +2 lines · +2 tokens per session 2f03b7eab75d
- 1mo ago Changed · +27 lines · +213 tokens per session a15b0a67e617
- 1mo ago First seen · 34 lines · 537 tokens per session scan A 4562dc788e6d
prism AGENTS.md is an instructions file published in the GitHub repository provasign/prism (7 stars, last pushed 4d ago), licensed Apache-2.0. It adds 638 tokens to every session, about $0.0026 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% 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.