agentmods.dev

devussy: Instructions file for Codex

AGENTS.md

devussy AGENTS.md is an instructions file for Codex, OpenCode from mojomast/devussy. It costs 1,834 tokens per session, scanned A, original, MIT.

Repository instructions for Devussy, a project that stores progress, phase tasks, and handoff notes in Markdown files. It uses stable HTML comments called anchors to identify the sections agents may read or update.

In plain words
What is it for?
Reading and updating progress logs, next-task lists, phase plans, phase results, and handoff status safely.
Why use it?
Anchors let agents update only the intended section of a planning file without disturbing other notes. The guide defines the required markers and their purposes.

Instructions file for CodexOpenCode

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

This is mojomast/devussy's own configuration. It tells Codex and OpenCode how to work on devussy 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 devussy configures →

not rated 22repo 11mo ago A scan 1,834 tokens original MIT
View source ↗ mojomast/devussy
Reuse

Borrowing it

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

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 devussy AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/mojomast/devussy/agents-md"><img src="https://agentmods.dev/badge/instructions/mojomast/devussy/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,834 This file is loaded in full into every session.
When invoked 1,834 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 $0.01834 $0.01834
Opus 5.5 $0.00734 $0.00734
Sonnet 5.5 $0.00367 $0.00367
Haiku 4.5 $0.00183 $0.00183

Measured 2mo ago against content hash 2b7b4e28e377, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

devussy 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 · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file provides guidance to agents when working with code in this repository.

🔗 CRITICAL: Anchor-Based Context Management

⚠️ READ THIS FIRST - This is the most important pattern in this project.

Devussy uses stable HTML comment anchors for efficient context management and safe file updates. All agents MUST use anchors when reading/writing devplan, phase, and handoff files.

Required Anchors

File Anchor Purpose
devplan.md <!-- PROGRESS_LOG_START --> / <!-- PROGRESS_LOG_END --> Track completed work
devplan.md <!-- NEXT_TASK_GROUP_START --> / <!-- NEXT_TASK_GROUP_END --> Current 3-5 tasks to execute
phase*.md <!-- PHASE_TASKS_START --> / <!-- PHASE_TASKS_END --> Phase-specific tasks
phase*.md <!-- PHASE_PROGRESS_START --> / <!-- PHASE_PROGRESS_END --> Outcomes and blockers
handoff_prompt.md <!-- QUICK_STATUS_START --> / <!-- QUICK_STATUS_END --> Status snapshot
handoff_prompt.md <!-- HANDOFF_NOTES_START --> / <!-- HANDOFF_NOTES_END --> Agent handoff notes

How to Use Anchors

Reading (CORRECT):

Read devplan.md lines between <!-- NEXT_TASK_GROUP_START --> and <!-- NEXT_TASK_GROUP_END -->
# Result: ~100 tokens loaded

Reading (WRONG):

Read entire devplan.md
# Result: ~3000 tokens wasted

Writing: Always use safe_write_devplan() from src/file_manager.py:

  • Creates .bak backup before writing
  • Validates anchors exist in new content
  • Refuses to overwrite if anchors missing (writes to .tmp instead)

Token Budget

File Section ~Tokens When to Read
handoff.md Progress Log ~200 Start of session
devplan.md NEXT_TASK_GROUP ~100 Every turn
devplan.md PROGRESS_LOG ~100 If needed
phase*.md PHASE_TASKS ~80 When working on phase

Target: Stay under 500 tokens per turn by reading ONLY anchored sections.

Read the full file on GitHub · 131 lines

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 · 131 lines · 1,834 tokens per session scan A 2b7b4e28e377

Subscribe to this mod's changes

devussy AGENTS.md is an instructions file published in the GitHub repository mojomast/devussy (22 stars, last pushed 11mo ago), licensed MIT. It adds 1,834 tokens to every session, about $0.0073 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.

Project management
Related

devussy AGENTS.md compared with instructions from other repositories

devussy AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
devussy AGENTS.mdmojomast/devussyInstructions file2211mo agoMITA1,834Codex, 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