agentmods.dev

agent-task: Instructions file for Codex

AGENTS.md

agent-task AGENTS.md is an instructions file for Codex, OpenCode from nyosegawa/agent-task. It costs 321 tokens per session, scanned A, original, MIT.

Project instructions for an agent-task application, including a test-first workflow and Rust checks.

In plain words
What is it for?
Use them when changing the Rust task application, its command-line behavior, dependencies, or append-only task-log handling.
Why use it?
They make expected behavior explicit before implementation and require formatting, tests, and warning-free linting before completion.

Instructions file for CodexOpenCode

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

This is nyosegawa/agent-task's own configuration. It tells Codex and OpenCode how to work on agent-task itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agent-task configures →

not rated 6repo 8mo ago A scan 321 tokens original MIT
View source ↗ nyosegawa/agent-task
Reuse

Borrowing it

Nothing to install: this file belongs to nyosegawa/agent-task. 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/nyosegawa/agent-task/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/nyosegawa/agent-task

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-task AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/nyosegawa/agent-task/agents-md/github.svg)](https://agentmods.dev/instructions/nyosegawa/agent-task/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/nyosegawa/agent-task/agents-md"><img src="https://agentmods.dev/badge/instructions/nyosegawa/agent-task/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.

agentmods 80×15 button for agent-task AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/nyosegawa/agent-task/agents-md"><img src="https://agentmods.dev/badge/instructions/nyosegawa/agent-task/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 321 This file is loaded in full into every session.
When invoked 321 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00321 $0.00321
Opus 5.5 $0.00128 $0.00128
Sonnet 5.5 $0.00064 $0.00064
Haiku 4.5 $0.00032 $0.00032

Measured 2mo ago against content hash 38a0ce9ec452, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agent-task 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 · 27 lines

What it actually says

AGENTS.md

Absolute Rules

  1. Instruction budget rule: keep this AGENTS.md in 20-30 lines.
  2. No backward compatibility: never preserve legacy behavior/interfaces.
  3. Commit and push regularly in small, reviewable increments.
  4. Refactor periodically to reduce complexity and technical debt.
  5. Always use the latest versions for libraries/dependencies, and research their usage thoroughly before introducing them.

Development Policy

  1. This repository is TDD-first by default.
  2. Always execute Red -> Green -> Refactor.
  3. Start with a failing test before production code.
  4. If tests are hard to write, create seams (split function, trait, adapter) and test through them.

Required Flow Per Change

  1. Define expected behavior as a test.
  2. Run tests and confirm failure (Red).
  3. Implement the minimal fix (Green).
  4. Refactor safely with tests green.
  5. Re-run full relevant scope before finishing.

Rust Verification Loop

  1. cargo test
  2. cargo fmt --check
  3. cargo clippy -- -D warnings

Task CLI Specifics

  • Storage: ~/.local/share/tasks/tasks.log (append-only JSONL, never edit/delete entries)
  • Project ID: git remote get-url origin → owner/repo format; fallback to cwd path
  • stdout output is the contract: TASK_ADD_{id}, TASK_{STATUS}_{id} (e.g. TASK_DOING_{id}, TASK_INREVIEW_{id})
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. 2mo ago First seen · 27 lines · 321 tokens per session scan A 38a0ce9ec452

Subscribe to this mod's changes

agent-task AGENTS.md is an instructions file published in the GitHub repository nyosegawa/agent-task (6 stars, last pushed 8mo ago), licensed MIT. It adds 321 tokens to every session, about $0.0013 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.

Related

agent-task AGENTS.md compared with instructions from other repositories

agent-task AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
agent-task AGENTS.mdnyosegawa/agent-taskInstructions file68mo agoMITA321Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode