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 5.5 | $0.00508 | $0.00508 |
| Sonnet 5.5 | $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 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.
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.
- 2mo 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 6mo ago), licensed MIT. It adds 1,270 tokens to every session, about $0.0051 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 2026-08-31.
the-last-repo AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| the-last-repo AGENTS.mdopinionated-unopinionated/the-last-repo | Instructions file | 2 | 6mo ago | MIT | A | 1,270 | 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 | 5,649 | 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 |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |