Borrowing it
Nothing to install: this file belongs to Sovea/stetra. 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/Sovea/stetra/main/AGENTS.mdgit clone --depth 1 https://github.com/Sovea/stetraWrote 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/sovea/stetra/agents-md)<a href="https://agentmods.dev/instructions/sovea/stetra/agents-md"><img src="https://agentmods.dev/badge/instructions/sovea/stetra/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/sovea/stetra/agents-md"><img src="https://agentmods.dev/badge/instructions/sovea/stetra/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 | $0.00407 | $0.00407 |
| Opus 5.5 | $0.00163 | $0.00163 |
| Sonnet 5.5 | $0.00081 | $0.00081 |
| Haiku 4.5 | $0.00041 | $0.00041 |
Grade A, and why
stetra 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 1mo 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stetra
Problem
Coding Agents can produce changes faster than developers can reconstruct their behavior, engineering choices, and limitations. Stetra keeps developer direction, engineering understanding, and authority connected to the actual work.
Core design
Stetra is a project layer inside the coding Host, with Codex as the primary Host. The Host owns conversation, model execution, implementation, and repair. Stetra connects five parts of one admitted coding task:
- Intent: exact developer direction, corrections, and Agent interpretation.
- Decision: engineering choices, alternatives, consequences, and authority.
- Observation: actual changes, executed checks, and retained evidence.
- Assessment: separately attributed analysis of behavior, mechanism, omissions, contradictions, and unknowns.
- Adoption: the developer's explicit decision about the current result.
Reconciliation relates assessed changes to direction, decisions, implementation claims, and observed evidence. It makes gaps inspectable so they can be repaired, explained, or decided by the developer. Existing authorization supports autonomous repair; new choices require developer input only when that authority is insufficient.
Developers own direction and final decisions. Agents own interpretation, implementation, and semantic judgment. Runtime owns observed facts, identity, ordering, persistence, and structural validation. These responsibilities remain distinct; passing checks or confident analysis cannot substitute for a developer decision.
Evidence remains inspectable across corrections. A decision binds to an exact current result; changed inputs invalidate that binding without erasing history.
Implementation boundary
Host adapter -> CLI -> Core. Core contains the deterministic task domain and
schemas. CLI owns repository IO, check execution, persistence, and presentation.
Model execution stays in the Host.
Admission and assurance follow explicit developer direction or project policy. Keep routine work small. Every required record or interaction must support a concrete alignment, repair, understanding, or decision need. Runtime must not infer semantic importance or authority through heuristics or scalar scores.
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.
- 1mo ago Changed · -135 lines · -1,236 tokens per session 14a490731cea
- 1mo ago Changed · -187 lines · -1,757 tokens per session ce721360d7b6
- 2mo ago First seen · 368 lines · 3,400 tokens per session scan A 44a718d63631
stetra AGENTS.md is an instructions file published in the GitHub repository Sovea/stetra (2 stars, last pushed 1mo ago), licensed MIT. It adds 407 tokens to every session, about $0.0016 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.
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).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.