Borrowing it
Nothing to install: this file belongs to signalridge/slipway. 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/signalridge/slipway/main/AGENTS.mdgit clone --depth 1 https://github.com/signalridge/slipwayWrote 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/signalridge/slipway/agents-md)<a href="https://agentmods.dev/instructions/signalridge/slipway/agents-md"><img src="https://agentmods.dev/badge/instructions/signalridge/slipway/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 | $0.00470 | $0.00470 |
| Opus 5 | $0.00235 | $0.00235 |
| Sonnet 5 | $0.00094 | $0.00094 |
| Haiku 4.5 | $0.00047 | $0.00047 |
Grade A, and why
slipway 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 8d 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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Slipway Agent Principles
Slipway is a user-invoked, interruptible soft autopilot for AI coding. This file states principles only. Command syntax and protocol fields belong to the CLI, the generated capabilities, and docs/reference/, not here.
This is the single principle file for every agent working in this repository. CLAUDE.md points here on purpose: two copies of these rules drifted into two different wordings once already.
User owns the process
- Never start Slipway on its own. A run begins only from explicit user intent.
- Honor skip, stop, resume, reorder, and manual takeover immediately. The user owes no reason.
- Ask for confirmation before a destructive operation. Do not require repeated approval for ordinary work that was already requested.
Investigate before clarifying
- Read the current Git state, relevant code, and repository build, test, typecheck, and lint conventions yourself.
- Ask zero questions when the request is complete, and proceed without repeated authorization.
- Ask only genuine human decisions that repository investigation cannot settle, one at a time, with a recommendation, rationale, and concrete alternatives.
- If clarification changes the implementation understanding, summarize the shared understanding and obtain one confirmation before implementation.
- Stop the interview immediately when the user asks to wrap up.
Report, do not certify
- Record exact commands, exit codes, changed files, findings, known issues, uncertainties, and activities not performed.
- Never present an unrun activity as run.
endedmeans the automatic Action queue is empty. It is not a judgement about the software.- Review is advisory and read-only. Findings never automatically trigger repair work.
- Report state the product can honor. Do not publish authority, an Action, or an observation that the current state contradicts.
Maintain the whole surface
- Keep the CLI, versioned protocol, host capabilities, docs, and tests consistent.
- Preserve unrelated work and user-modified managed files.
- Never make an agent guess its next step. A pause or error names the operation and its typed inputs; if the public surface leaves the next command to guesswork, fix that surface.
- Do not reintroduce retired commands, ambient hooks, old-state readers, dual runtime behavior, or compatibility aliases. Remove retired behavior instead.
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.
- 8d ago First seen · 35 lines · 470 tokens per session scan A ead1710a4fa4
slipway AGENTS.md is an instructions file published in the GitHub repository signalridge/slipway (23 stars, last pushed yesterday), licensed BSD-3-Clause. It adds 470 tokens to every session, about $0.0024 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
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.