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/pome-sh/digital-twins/agents-mdgit clone --depth 1 https://github.com/pome-sh/digital-twinsWrote 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/pome-sh/digital-twins/agents-md)<a href="https://agentmods.dev/instructions/pome-sh/digital-twins/agents-md"><img src="https://agentmods.dev/badge/instructions/pome-sh/digital-twins/agents-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 5.1 | $0.02650 | $0.02650 |
| Opus 5 | $0.01325 | $0.01325 |
| Sonnet 5 | $0.00530 | $0.00530 |
| Haiku 4.5 | $0.00265 | $0.00265 |
Grade A, and why
digital-twins 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 2d 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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Intro
Open-sourced Digital Twins of APIs and the pome CLI.
A digital twin is a local, resettable emulation of a real API that answers the same REST, GraphQL and MCP calls your agent makes in production, backed by real SQLite state. The CLI boots a twin, runs an agent against it, and records the trace.
Recording is open source. Evaluation and scoring are hosted: pome run --local
records a trace. Apache-2.0.
Layout
cli/ the `pome` CLI
src/cli/ one file per command; main.ts is the Commander tree
src/runner/ boots twins, runs the agent, writes artifacts
src/recorder/ trace capture and redaction
src/hosted/ control-plane client
src/task/ task file parsing
tasks/ the bundled task library `pome tasks` serves
packages/
twin-{github,gmail,linear,slack,stripe}/
sdk/ the HTTP + MCP server every twin mounts, route input
declaration, seed loading
wire/ event and trace types crossing a process boundary
checks/ the check DSL and the twins' check declarations
sandbox-domains/ the same twins with no server — domain object, SQLite
opener, seed parser, for reading state in-process
contract/ cross-package tests against a booted twin
scripts/ build and CI gates
skills/ Claude skills shipped as a plugin
agent-examples/ runnable AGENTS for Pome to grade, each with its own install
integration-examples/ harnesses that DRIVE Pome from another eval platform
Commands
npm test # every vitest test in the repo, one process
npm run typecheck # every workspace
npm run build # every workspace, dependency-ordered
npm run test:contract # contract/ suite, needs a built cli/
npm run test:pack # installs both tarballs in a clean room
npm run gate:examples # typechecks + tests every example, own install
npm run smoke:examples # launches every example for real
npm run lint:dead-code # knip
npm run lint # every lint rule, one runner
npm run lint -- <rule> # one rule, for local iteration
npm run lint -- --list # what rules exist
npm run lint:test # each rule's case table
npm run probe:twins # every declared endpoint answers
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.
- 2d ago Changed · -1 lines · -25 tokens per session b6d319392429
- 6d ago First seen · 215 lines · 2,675 tokens per session scan A d38babc795b0
digital-twins AGENTS.md is an instructions file published in the GitHub repository pome-sh/digital-twins (14 stars, last pushed today), licensed Apache-2.0. It adds 2,650 tokens to every session, about $0.0132 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 2026-08-30.
Other instructions, from other repositories
kungfu copilot-instructions.md
Copilot instructions for kungfu-systems/kungfu: Read and follow AGENTS.md before proposing or running changes. It is the shared agent router for this repository, including the canonical Shifu development and build entrypoint.
agents CLAUDE.md
Instructions for eloylp/agents, covering claude.md, project overview, directory structure, config model and build & run.
ideate AGENTS.md
Instructions for paultyng/ideate, covering agents.md, build features as mcp tools first, ui second, when to add ui and pattern.
icron CLAUDE.md
Instructions for zebbern/icron, covering icron, architecture, key directories, built-in tools and commands.
workstreams disposable.instructions.md
Guidelines for writing code using IDisposable.
relay CLAUDE.md
Claude Code instructions for simota/relay, covering claude.md, what this is, documentation map, runtime: bun-first and commands.