Borrowing it
Nothing to install: this file belongs to evilmartians/agent-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/evilmartians/agent-prism/main/AGENTS.mdgit clone --depth 1 https://github.com/evilmartians/agent-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/evilmartians/agent-prism/agents-md)<a href="https://agentmods.dev/instructions/evilmartians/agent-prism/agents-md"><img src="https://agentmods.dev/badge/instructions/evilmartians/agent-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/evilmartians/agent-prism/agents-md"><img src="https://agentmods.dev/badge/instructions/evilmartians/agent-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 | $0.00875 | $0.00875 |
| Opus 5.5 | $0.00350 | $0.00350 |
| Sonnet 5.5 | $0.00175 | $0.00175 |
| Haiku 4.5 | $0.00088 | $0.00088 |
Grade A, and why
agent-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 28d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agent-prism
Packages
| Package | Role | Published |
|---|---|---|
types |
Trace types and attribute constants; source of truth for every type | npm, ESM only |
data |
Adapters (Langfuse, OpenTelemetry) and pure helpers over types |
npm, ESM only |
ui |
React components users copy into their projects; imports data, types |
no, copied from source |
storybook |
Stories for ui, run as tests |
no, deployed to Firebase |
demo-app |
Vite sandbox | no |
saas |
Next.js trace explorer | no, deployed to Firebase |
Rules
| Rule | Enforced by |
|---|---|
Relative imports in types and data end in .js |
pnpm lint:check (import/extensions), pnpm lint:packages |
Imports in ui and the apps have no extension (?raw, .css, .json excepted) |
pnpm lint:check (import/extensions) |
types and data never import React, ui or an app; types never imports data; ui never imports an app |
pnpm lint:check (boundaries/dependencies) |
No // comments; JSDoc only in types, data, ui |
pnpm lint:check (comments/no-comments) |
Strict TypeScript, no any, no unchecked index access |
pnpm tsc, pnpm lint:check |
Type-aware rules in .ts/.tsx: no floating promises, no unsafe any, strict booleans, readonly params |
pnpm lint:check (--type-aware, tsgolint) |
| Prettier formatting | pnpm format:check |
data tests run in UTC and keep coverage above the thresholds in packages/data/vitest.config.ts |
pnpm test --coverage |
| No unused files, exports or dependencies | pnpm knip |
No copy-pasted code anywhere (10 lines); in types and data (tests included) not even 6 lines |
pnpm jscpd |
No type in any package that spells out one from packages/types, no two identical object shapes |
pnpm dup:types |
Stories render and pass axe; color-contrast is off until #107 |
pnpm test:storybook |
packages/ui/src/components/theme is generated from packages/ui/src/theming/theme.ts |
pnpm theme:check |
Published types and data resolve for consumers |
pnpm lint:packages (publint, attw) |
ui compiles against types and data as published on npm: release new API before ui uses it |
pnpm ui:npm |
| Workflows pass zizmor | check-workflows.yaml |
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.
- 28d ago First seen · 49 lines · 875 tokens per session scan A 0755d5428311
agent-prism AGENTS.md is an instructions file published in the GitHub repository evilmartians/agent-prism (404 stars, last pushed 29d ago), licensed MIT. It adds 875 tokens to every session, about $0.0035 per session on Opus 5.5. 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 2026-10-09.
agent-prism AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| agent-prism AGENTS.mdevilmartians/agent-prism | Instructions file | 404 | 29d ago | MIT | A | 875 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |