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/2youg1/sprawling/agents-mdgit clone --depth 1 https://github.com/2youg1/sprawlingWhat 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 | $0.02019 | $0.02019 |
| Opus 5 | $0.01009 | $0.01009 |
| Sonnet 5 | $0.00404 | $0.00404 |
| Haiku 4.5 | $0.00202 | $0.00202 |
Grade A, and why
sprawling 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 3d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — how work is done in this repository
For any agent or person about to change this code. Read this file to the end before the first edit; it is short on purpose, and everything it does not cover is one link away.
sprawling is a locally deployed agent-city harness: one Rust binary, a WebAssembly client embedded inside it, and a city that keeps its whole history in one append-only Ledger. Most of it was written by models, and every rule below exists for one reason that applies to a person just as much: a contributor who does not remember yesterday still has to produce work that holds.
The loop
cargo install just cargo-nextest --locked # once; the toolchain installs itself from rust-toolchain.toml
just check # fmt + clippy (-D warnings, --all-features) + nextest + every machine gate
A change is finished when just check is green. "I finished it" is a claim; a green run is the evidence.
| Command | What it does |
|---|---|
just check |
the closing condition for every change |
just gates |
the machine gates alone |
just check-web |
clippy on the wasm target — the two places just check cannot reach |
just build-web |
build the client bundle, without dx |
just dist |
the whole deliverable: client, binary, bill of materials, size badges |
just sim [seed] |
citysim scenarios; a failure reproduces from its seed |
just spec <crate> |
generate a SPEC skeleton |
just api-baseline |
recompute the public-surface baselines |
just replay <log> |
verify a ledger chain offline, read-only |
just mem [pid] / just bench / just budget |
the measurements, in this platform's own vocabulary |
just fuzz <target> / just mutants |
fuzz targets / mutation testing |
Read before you write
ARCHITECTURE.md— what the code is made of, how the twelve crates are wired, what one dispatch does end to end. Itsdepmapblock and module map are machine authorities.- The SPEC of the crate you are touching,
crates/<crate>/<crate>-SPEC.md— the interfaces and decisions, written before the code. docs/glossary.md— one name per concept, enforced by a gate.- The tests next to the code you are about to change.
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.
- 3d ago First seen · 100 lines · 2,019 tokens per session scan A 3e0886237ae6
sprawling AGENTS.md is an instructions file published in the GitHub repository 2youg1/sprawling (91 stars, last pushed 4d ago), licensed MPL-2.0. It adds 2,019 tokens to every session, about $0.0101 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
learn-harness-engineering CLAUDE.md
Instructions for walkinglabs/learn-harness-engineering, covering claude.md, project overview, commands, documentation site and run lecture code examples.
trueforge AGENTS.md
AGENTS.md instructions for truefoundry/trueforge, a project described as: The open-source agent harness - the runtime layer that turns an LLM into a working agent.
Lody AGENTS.md
Instructions for LodyAI/Lody, covering repository guidelines, context maintenance, repository boundary, project map and checks and commits.
opencode-plusplus AGENTS.md
Instructions for whut09/opencode-plusplus, covering agent guide, generated agent guide, must-read rules, default workflow and project entrypoints.
duet-agent AGENTS.md
Instructions for dzhng/duet-agent, covering agent guidelines, treat types as documentation, keep names current, keep comments useful and prefer direct, local guarantees.
hyper-waterfall AGENTS.md
Instructions for postmelee/hyper-waterfall, covering agents.md, 프로젝트 개요, 하이퍼-워터폴 핵심 규칙, 명명 규칙 and 핵심 강제 규칙 (변경 전 매뉴얼 확인 필수).