Borrowing it
Nothing to install: this file belongs to adrienm7/ergopti. 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/adrienm7/ergopti/main/AGENTS.mdgit clone --depth 1 https://github.com/adrienm7/ergoptiWrote 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/adrienm7/ergopti/agents-md)<a href="https://agentmods.dev/instructions/adrienm7/ergopti/agents-md"><img src="https://agentmods.dev/badge/instructions/adrienm7/ergopti/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/adrienm7/ergopti/agents-md"><img src="https://agentmods.dev/badge/instructions/adrienm7/ergopti/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 | $0.00806 | $0.00806 |
| Opus 5.5 | $0.00322 | $0.00322 |
| Sonnet 5.5 | $0.00161 | $0.00161 |
| Haiku 4.5 | $0.00081 | $0.00081 |
Grade A, and why
ergopti 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 15d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shared repository contract
This is the small common startup context for Codex, Claude Code, GitHub Copilot, Gemini CLI, and other repository agents. Keep detailed procedures in skills and durable technical knowledge in routed memory.
Safety
- Preserve unrelated working-tree and index changes. Stage exact owned paths; never use a broad add, stash, reset, clean, or worktree move as a shortcut.
- Treat registered sibling worktrees as active user state. Do not modify, delete, or relocate one unless the current request explicitly puts it in scope.
- Reuse owned worktrees instead of creating a full repository copy per probe. Once no task, gate, or retained process needs one, archive it with a recoverable Git snapshot and remove its unused ignored caches. Keep compact proof files rather than complete duplicate checkouts.
- Measure storage before large validations and clean confirmed unused owned temporary files at completed checkpoints. Age alone does not prove that a workspace is inactive; never delete conversation history databases.
- Never push
devormainwithout explicit authorization in the current conversation. Commits and green tests do not imply push permission. - Never stop, edit-and-resume or relaunch a running multi-agent workflow to add
a new requirement; route it to a follow-up run (skill
workflow-change-control). - Store text as LF on every OS. AutoHotkey source additionally keeps its UTF-8 BOM; use the repository encoding gate after touching it.
Context routing
- Before non-trivial work, read docs/memory/README.md, then only the topics it routes for the current surface.
- Reusable procedures live canonically in
.agents/skills/. Select skills by their descriptions and load only matchingSKILL.mdbodies and references..claude/skills/is a generated mirror; never edit it directly. - Use the project launcher documented in docs/tooling/rtk.md when command output is read by a human or LLM. Invoke the child directly when stdout feeds a pipe, redirection, parser, hash, generator, or test assertion. CI remains network-independent and can execute the child command unfiltered.
- A small, local, low-risk edit does not require a formal or persisted plan. Use a plan for multi-step, cross-driver, high-risk, or audit-campaign work.
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.
- 15d ago First seen · 65 lines · 806 tokens per session scan A f31390b13469
ergopti AGENTS.md is an instructions file published in the GitHub repository adrienm7/ergopti (14 stars, last pushed today), licensed MIT. It adds 806 tokens to every session, about $0.0032 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 2026-10-14.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.