Evidence is a code-based business intelligence tool for building interactive data reports from SQL queries and Markdown instead of using drag-and-drop dashboards. It is used by people who need to create, publish, or self-host data visualizations and reports. The catalogue entries are instructions for working with Evidence.
Borrowing it
Nothing to install: this file belongs to evidence-dev/evidence. 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/evidence-dev/evidence/main/AGENTS.mdgit clone --depth 1 https://github.com/evidence-dev/evidenceWrote 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/evidence-dev/evidence/agents-md)<a href="https://agentmods.dev/instructions/evidence-dev/evidence/agents-md"><img src="https://agentmods.dev/badge/instructions/evidence-dev/evidence/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/evidence-dev/evidence/agents-md"><img src="https://agentmods.dev/badge/instructions/evidence-dev/evidence/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 | $0.00289 | $0.00289 |
| Opus 5.5 | $0.00116 | $0.00116 |
| Sonnet 5.5 | $0.00058 | $0.00058 |
| Haiku 4.5 | $0.00029 | $0.00029 |
Grade A, and why
evidence 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 2mo 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.
What it actually says
Agents.md
Evidence is an agent-ready tool for creating reports from your data — markdown with inline SQL, rendered as interactive reports.
This repo is a mirror
This is a read-only projection of a larger repo, kept in sync automatically. Open PRs as normal and changes will be upstreamed. See CONTRIBUTING.md for details.
Don't add or rename files at the repo root, as they will not be synced.
Layout
core/— library containing user components, query engine, rendering primitives.cli/— theevidenceCLI which renders interactive reports. Built with Bun.docs/patches/
Scripts
Requires Node 22.22+, pnpm and bun.
| Task | Command |
|---|---|
| Install | pnpm install |
Build the CLI (to cli/dist/evidence) |
pnpm cli:build |
| Unit tests | pnpm test |
| Type check | pnpm check |
| Run the CLI locally (against the fixture project) | pnpm evd |
| Docs site | pnpm docs:dev |
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.
- 2mo ago First seen · 31 lines · 289 tokens per session scan A 9bafd6063eb8
evidence AGENTS.md is an instructions file published in the GitHub repository evidence-dev/evidence (7,092 stars, last pushed yesterday), licensed MIT. It adds 289 tokens to every session, about $0.0012 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 2026-08-30.
evidence AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| evidence AGENTS.mdevidence-dev/evidence | Instructions file | 7.1k | yesterday | MIT | A | 289 | 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 |