agent-regress AGENTS.md

agent-regress AGENTS.md is an instructions file for Codex, OpenCode from Gaurav7974/agent-regress. It costs 400 tokens per session, scanned A, original, MIT.

Repository instructions for AI coding agents working on agent-regress, a local server for testing coding agents with repeatable checks.

In plain words
What is it for?
They guide work on regression tests, deterministic checks, semantic-test handling, safe history-file updates, and cleanup of timed-out processes.
Why use it?
They give agents the project background, required commands, and rules that prevent them from breaking important test and file-handling behavior.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/gaurav7974/agent-regress/agents-md
Clone the repo
git clone --depth 1 https://github.com/Gaurav7974/agent-regress

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for agent-regress AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/gaurav7974/agent-regress/agents-md.svg)](https://agentmods.dev/instructions/gaurav7974/agent-regress/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/gaurav7974/agent-regress/agents-md"><img src="https://agentmods.dev/badge/instructions/gaurav7974/agent-regress/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 400 This file is loaded in full into every session.
When invoked 400 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00400 $0.00400
Opus 5 $0.00200 $0.00200
Sonnet 5 $0.00080 $0.00080
Haiku 4.5 $0.00040 $0.00040

Measured 5d ago against content hash d4cd23a35e17, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

agent-regress 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 5d 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.

AGENTS.md · 26 lines

What it actually says

AGENTS.md

Repository Context

This file serves as a system prompt and context guide for any AI coding agents that open this repository.

Project: agent-regress - A local MCP server that provides tools to run regression tests against AI coding agents using deterministic code checks.

Key Directives

  1. Semantic Evaluation is Deferred: The current architecture intentionally defers semantic evaluation (AI-judged tests) until post-MVP. If an eval specifies pass_criteria.type: "semantic", the execute_eval tool must return a hardcoded SKIPPED_SEMANTIC_MVP status. Do not attempt to implement semantic evaluation logic.
  2. Deterministic Checks Only: All evaluations must rely solely on standard deterministic criteria (regex, JSON schema, exit code, exact match). Do not use AI to judge tests.
  3. Atomic File Operations: The .eval_history/manifest.json file uses a temporary file write and a retry-based rename loop to avoid race conditions with concurrent readers on Windows. Do not simplify this logic.
  4. Process Tree Cleanup: execute_eval uses taskkill /F /T on Windows and -PID process group termination on Unix to prevent orphaned subprocesses during timeouts.

Build & Test Commands

  • Install Dependencies: npm install
  • Build: npm run build
  • Run Tests:
    • npm run test:list-evals (list_evals)
    • npm run test:cli-execution (CLI execution & timeouts)
    • npm run test:http-execution (HTTP execution & schema validation)
    • npm run test:validation-and-history (Validation logic & atomic writes)
    • npm run test:diffing (Baseline & Regression diffing)
    • npm test (Run all suites)
Changes

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.

  1. 5d ago First seen · 26 lines · 400 tokens per session scan A d4cd23a35e17

Subscribe to this mod's changes

agent-regress AGENTS.md is an instructions file published in the GitHub repository Gaurav7974/agent-regress (0 stars, last pushed 1mo ago), licensed MIT. It adds 400 tokens to every session, about $0.0020 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.

Related

Other instructions, from other repositories