Borrowing it
Nothing to install: this file belongs to opinionated-unopinionated/the-last-repo. 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/opinionated-unopinionated/the-last-repo/main/AGENTS.mdgit clone --depth 1 https://github.com/opinionated-unopinionated/the-last-repoWrote 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/opinionated-unopinionated/the-last-repo/agents-md)<a href="https://agentmods.dev/instructions/opinionated-unopinionated/the-last-repo/agents-md"><img src="https://agentmods.dev/badge/instructions/opinionated-unopinionated/the-last-repo/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/opinionated-unopinionated/the-last-repo/agents-md"><img src="https://agentmods.dev/badge/instructions/opinionated-unopinionated/the-last-repo/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 | $0.01270 | $0.01270 |
| Opus 5 | $0.00635 | $0.00635 |
| Sonnet 5 | $0.00254 | $0.00254 |
| Haiku 4.5 | $0.00127 | $0.00127 |
Grade A, and why
the-last-repo 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 12d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — The Last Repo
You are an AI coding agent working in this repository. This file is your entry point. Read it first, then load only what you need for the task in front of you. The repo follows progressive disclosure: smallest, most general context first; deeper docs are fetched on demand.
Reading order
- This file. Orientation, mandates, and pointers.
docs/README.md— map ofspecs/,plans/,adr/and their scoped subfolders.- The relevant scoped folder — e.g.
docs/plans/<scope>/when implementing a plan,docs/adr/<scope>/when checking past architectural decisions. - Templates (
docs/<type>/TEMPLATE.md) — load only when authoring a new doc of that type.
Do not pre-read templates or unrelated scopes. Load context lazily.
Key paths
| Path | Purpose |
|---|---|
AGENTS.md |
Canonical AI context (this file). CLAUDE.md is a symlink to it. |
PROMPT.md |
Default Ralph loop prompt fed to the harness each iteration. |
scripts/ralph.sh |
Loop driver. Re-invokes the chosen harness until the agent creates the sentinel file .ralph/COMPLETE. |
scripts/harness.sh |
Dispatches to pi, claude, or codex. |
scripts/new-{spec,plan,adr}.sh |
Generators that copy the matching template into <scope>/<NNNN>-<slug>.md. |
Makefile |
One entry point for ralph, new-*, lint-docs, ci. Run make help. |
docs/specs/ |
Product/feature intent. What and why. |
docs/plans/ |
Executable checklists. How and in what order. Each plan must have a §6 Checklist and §7 Loop Recipe. |
docs/adr/ |
Architectural decisions, Nygard-style. |
apps/, services/, packages/, tools/ |
Polyglot monorepo shells. Each has a README defining conventions. |
.ralph/logs/last.log |
Ralph loop iteration log. Append-only, one line per iteration. |
The Ralph-loop mandate
Non-trivial work in this repo is driven by a Ralph Wiggum loop, not by ad-hoc multi-step sessions. The loop is the contract:
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.
- 12d ago First seen · 69 lines · 1,270 tokens per session scan A 4a74b7697e8f
the-last-repo AGENTS.md is an instructions file published in the GitHub repository opinionated-unopinionated/the-last-repo (2 stars, last pushed 4mo ago), licensed MIT. It adds 1,270 tokens to every session, about $0.0064 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 2026-08-31.
Other instructions, from other repositories
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.
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).
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.
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).