What is repo-task-proof-loop AGENTS.md?

A proof workflow for substantial code changes that records requirements, implementation evidence, verification results, and any remaining problems.

Use it for major features, refactors, and bug fixes that need a frozen specification, recorded evidence, fresh checks, and possibly a fix-and-retest cycle.

It prevents an agent from claiming a task is finished without checking the current code against every acceptance criterion.

How DenisSergeevitch/repo-task-proof-loop configures Codex and OpenCod

Reuse

Borrowing it

Nothing to install: this file belongs to DenisSergeevitch/repo-task-proof-loop. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/DenisSergeevitch/repo-task-proof-loop/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/DenisSergeevitch/repo-task-proof-loop

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/denissergeevitch/repo-task-proof-loop/agents-md/github.svg)](https://agentmods.dev/instructions/denissergeevitch/repo-task-proof-loop/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/denissergeevitch/repo-task-proof-loop/agents-md"><img src="https://agentmods.dev/badge/instructions/denissergeevitch/repo-task-proof-loop/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/denissergeevitch/repo-task-proof-loop/agents-md"><img src="https://agentmods.dev/badge/instructions/denissergeevitch/repo-task-proof-loop/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 422 This file is loaded in full into every session.

When invoked 422 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00422	$0.00422
Opus 5.5	$0.00169	$0.00169
Sonnet 5.5	$0.00084	$0.00084
Haiku 4.5	$0.00042	$0.00042

Measured 2mo ago against content hash b9743a535774, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

repo-task-proof-loop 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.

AGENTS.md · 30 lines

What it actually says

Repo task proof loop

For substantial features, refactors, and bug fixes, use the repo-task-proof-loop workflow.

Required artifact path:

Keep all task artifacts in .agent/tasks/<TASK_ID>/ inside this repository.

Required sequence:

Freeze .agent/tasks/<TASK_ID>/spec.md before implementation.
Implement against explicit acceptance criteria (AC1, AC2, ...).
Create evidence.md, evidence.json, and raw artifacts.
Run a fresh verification pass against the current codebase and rerun checks.
If verification is not PASS, write problems.md, apply the smallest safe fix, and reverify.

Hard rules:

Do not claim completion unless every acceptance criterion is PASS.
Verifiers judge current code and current command results, not prior chat claims.
Fixers should make the smallest defensible diff.
For broad Codex tasks, bounded fan-out is allowed only after init, only when the user has explicitly asked for delegation or parallel agent work, and only when task shape warrants it: use bounded explorer children before or after spec freeze, use bounded worker children only after the spec is frozen, keep the task tree shallow, keep evidence ownership with one builder, and keep verdict ownership with one fresh verifier.
This root AGENTS.md block is the repo-wide Codex baseline. More-specific nested AGENTS.override.md or AGENTS.md files still take precedence for their directory trees.
Keep this block lean. If the workflow needs more Codex guidance, prefer nested AGENTS.md / AGENTS.override.md files or configured fallback guide docs instead of expanding this root block indefinitely.

Installed workflow agents:

.codex/agents/task-spec-freezer.toml
.codex/agents/task-builder.toml
.codex/agents/task-verifier.toml
.codex/agents/task-fixer.toml

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.

2mo ago First seen · 30 lines · 422 tokens per session scan A b9743a535774

Subscribe to this mod's changes

repo-task-proof-loop AGENTS.md is an instructions file published in the GitHub repository DenisSergeevitch/repo-task-proof-loop (726 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 422 tokens to every session, about $0.0017 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 2026-08-30.

repo-task-proof-loop AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
repo-task-proof-loop AGENTS.mdDenisSergeevitch/repo-task-proof-loop	Instructions file	726	7mo ago	Apache-2.0	A	422	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

repo-task-proof-loop: Instructions file for Codex