mache AGENTS.md

A set of instructions for coding agents working in the agentic-research/mache project. It documents the rsry command-line tool used to track work items and lists shell commands that avoid confirmation prompts.

In plain words
What is it for?
Listing, reviewing, commenting on, closing, and exporting rsry work items, plus safely running copy, move, delete, SSH, and package-install commands.
Why use it?
It helps agents follow the project's workflow and prevents file operations from waiting for interactive approval.

Instructions file for CodexOpenCode

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/agentic-research/mache/agents-md
Clone the repo
git clone --depth 1 https://github.com/agentic-research/mache

Made for: Codex, OpenCode.

Per session 1,258 This file is loaded in full into every session.
When invoked 1,258 The same file — it is already loaded in full.
Security scan C 1 finding. 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 $0.01258 $0.01258
Opus 5 $0.00629 $0.00629
Sonnet 5 $0.00252 $0.00252
Haiku 4.5 $0.00126 $0.00126

Measured 2d ago against content hash f3c9406d8a20, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

mache AGENTS.md scanned grade C with 1 finding 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 2d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf directory # NOT: rm -r directory
AGENTS.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Instructions

This project uses rsry for bead tracking.

Quick Reference

rsry bead --repo . list --status ready
rsry bead --repo . review <id>
rsry bead --repo . comment add <id> "progress note"
rsry bead --repo . close <id>
rsry bead --repo . export --status all --jsonl -o .beads/beads.jsonl

Non-Interactive Shell Commands

ALWAYS use non-interactive flags with file operations to avoid hanging on confirmation prompts.

Shell commands like cp, mv, and rm may be aliased to include -i (interactive) mode on some systems, causing the agent to hang indefinitely waiting for y/n input.

Use these forms instead:

# Force overwrite without prompting
cp -f source dest           # NOT: cp source dest
mv -f source dest           # NOT: mv source dest
rm -f file                  # NOT: rm file

# For recursive operations
rm -rf directory            # NOT: rm -r directory
cp -rf source dest          # NOT: cp -r source dest

Other commands that may prompt:

  • scp - use -o BatchMode=yes for non-interactive
  • ssh - use -o BatchMode=yes to fail instead of prompting
  • apt-get - use -y flag
  • brew - use HOMEBREW_NO_AUTO_UPDATE=1 env var

Issue Tracking with rsry Beads

IMPORTANT: This project uses rsry beads for ALL issue tracking. Do NOT use markdown TODOs, task lists, or external issue trackers.

Why rsry?

  • Dependency-aware: Track blockers and relationships between issues
  • Version-controlled: bead content is shared through .beads/beads.jsonl
  • Agent-optimized: JSON output, ready work detection, discovered-from links
  • Prevents duplicate tracking systems and confusion

Quick Start

Check for ready work:

rsry bead --repo . list --status ready

Create new issues:

rsry bead --repo . create "Issue title" -d "Detailed context" -t bug|feature|task -p 0

Review and update:

rsry bead --repo . review <id>
rsry bead --repo . comment add <id> "What changed / what remains"

Read the full file on GitHub · 154 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. 2d ago First seen · 154 lines · 1,258 tokens per session scan C f3c9406d8a20

Subscribe to this mod's changes

mache AGENTS.md is an instructions file published in the GitHub repository agentic-research/mache (45 stars, last pushed 3d ago), licensed Apache-2.0. It adds 1,258 tokens to every session, about $0.0063 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.