compact-plus AGENTS.md

A set of project instructions for compact-plus, a plugin that preserves and restores an agent’s working state when its conversation is shortened. It defines which files and scripts write and read that recovery state.

In plain words
What is it for?
Use it when developing or maintaining compact-plus, including its recovery scripts, shared temporary state, external dependencies, and hook behavior.
Why use it?
It gives the plugin and its scripts shared rules for recovering context after compaction. It also limits changes to the compact-plus project instead of the base repository or configuration distribution files.

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/u-ichi/compact-plus/agents-md
Clone the repo
git clone --depth 1 https://github.com/u-ichi/compact-plus

Made for: Codex, OpenCode.

Per session 1,627 This file is loaded in full into every session.
When invoked 1,627 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 $0.01627 $0.01627
Opus 5 $0.00813 $0.00813
Sonnet 5 $0.00325 $0.00325
Haiku 4.5 $0.00163 $0.00163

Measured 2d ago against content hash 1c7f43cdd53d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

compact-plus 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 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.

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 · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

compact-plus Project Instructions

This repository manages the Claude Code and Codex plugin that preserves and restores working state around context compaction.

Scope

  • This repository manages only the compact-plus plugin itself.
  • Do not change the base repository home/, install.sh, or Claude/Codex configuration distribution scripts.

Shared State

path writer reader purpose
${TMPDIR:-/tmp}/claude-compact-state/<session_id>.md precompact-state-summary.sh / /compact-plus skill userpromptsubmit-compaction-recovery.sh / agent pre-compaction recovery state
${TMPDIR:-/tmp}/claude-compact-state-offset/<session_id> precompact-state-summary.sh precompact-state-summary.sh incremental byte offset
${TMPDIR:-/tmp}/claude-compact-state-counter/<session_id> precompact-state-summary.sh precompact-state-summary.sh refresh cycle counter
${TMPDIR:-/tmp}/claude-compacted/<session_id> compaction-recovery.sh userpromptsubmit-compaction-recovery.sh PostCompact marker
${TMPDIR:-/tmp}/claude-compact-warn/<session_id> statusline side userpromptsubmit-compact-plus-reminder.sh compact-plus suggestion marker
${TMPDIR:-/tmp}/claude-compact-warned/<session_id> userpromptsubmit-compact-plus-reminder.sh statusline side / compaction-recovery.sh suggestion cooldown marker
${TMPDIR:-/tmp}/claude-active-plan/<session_id> plan-management hook userpromptsubmit-compaction-recovery.sh active plan file pointer
${TMPDIR:-/tmp}/codex-compact-state/<thread_id>.md precompact-state-summary.sh / /compact-plus skill sessionstart-compaction-recovery.sh / agent Codex pre-compaction recovery state
${TMPDIR:-/tmp}/codex-compact-state-offset/<thread_id> precompact-state-summary.sh precompact-state-summary.sh Codex incremental byte offset
${TMPDIR:-/tmp}/codex-compact-state-counter/<thread_id> precompact-state-summary.sh precompact-state-summary.sh Codex refresh cycle counter
${TMPDIR:-/tmp}/codex-compacted/<thread_id> compaction-recovery.sh sessionstart-compaction-recovery.sh Codex PostCompact marker
${TMPDIR:-/tmp}/codex-compact-warned/<thread_id> userpromptsubmit-compact-plus-reminder.sh reminder / recovery hook Codex notification cooldown

Read the full file on GitHub · 91 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 · 91 lines · 1,627 tokens per session scan A 1c7f43cdd53d

Subscribe to this mod's changes

compact-plus AGENTS.md is an instructions file published in the GitHub repository u-ichi/compact-plus (201 stars, last pushed 1mo ago), licensed MIT. It adds 1,627 tokens to every session, about $0.0081 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 2026-08-30.

Related

Other instructions, from other repositories

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens