agentmods.dev

SaneProcess AGENTS.md

A project-specific instruction file for SaneProcess, the shared operating guide for SaneApps coding and release work.

In plain words
What is it for?
Use it when working on SaneApps code, hooks, releases, documentation, security checks, or session handoffs.
Why use it?
It tells agents which rules belong in the instruction file, where enforced workflows live, and how to communicate during a session.

Instructions file for CodexOpenCode

11 11d ago B scan 4,303 tokens original MIT
View the source file sane-apps/SaneProcess
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/sane-apps/saneprocess/agents-md
Clone the repo
git clone --depth 1 https://github.com/sane-apps/SaneProcess

Made for: Codex, OpenCode.

Per session 4,303 This file is loaded in full into every session.
When invoked 4,303 The same file — it is already loaded in full.
Security scan B 2 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 $0.04303 $0.04303
Opus 5 $0.02152 $0.02152
Sonnet 5 $0.00861 $0.00861
Haiku 4.5 $0.00430 $0.00430

Measured 3d ago against content hash 2933ee089c67, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

SaneProcess AGENTS.md scanned grade B with 2 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 3d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

Read relevant repo hooks in scripts/hooks/ and active client config when present (`~/.codex/config.toml`, `~/.claude/settings.json`) BEFORE doing work.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl. For campaign receipts, run `check-inbox.sh campaign-audit --subject "..."
AGENTS.md · 365 lines

How it starts

The opening of the file, as written. The whole thing — 365 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SaneApps AGENTS

SaneProcess is the shared SaneApps operating harness. This file is the active agent overlay, not the full runbook. Detailed implementation, release, Mini, and operator setup notes live in DEVELOPMENT.md, ARCHITECTURE.md, DEVELOPER_SETUP.md, templates/RELEASE_SOP.md, and scripts/.

Speak plainly and briefly. Use singular voice for SaneApps communications: I, me, my; never we, us, or our.

What Belongs Here

Keep only instructions an agent must know before hooks or wrappers can help. If a rule is already enforced by a hook, SaneMaster command, or test receipt, prefer pointing to that mechanism instead of duplicating the whole policy here.

Hard enforcement lives in:

  • scripts/hooks/ for launch, build-route, release, email, GitHub, tracking, session-end, security, visual-proof, GUI-feedback-loop, and completion gates.
  • scripts/SaneMaster.rb and scripts/sanemaster/ for canonical workflows.
  • scripts/validation_report.rb, process_eval, sop_review, near_miss_review, and tests for repeatable process health evidence.
  • SESSION_HANDOFF.md, .claude/research.md, agent file memory, and Mini-owned AgentMemory for active context and durable learnings. Serena is code-navigation only; its memories were absorbed into AgentMemory.

Session Start

For tiny read-only answers or one local command, read the relevant file/command surface and answer. For code, audit, release, support, payment, App Store, automation, UI/runtime, or multi-file work:

  1. Read SESSION_HANDOFF.md.
  2. Read relevant file memory and the active skill registry; query shared context with AgentMemory memory_recall or memory_smart_search.
  3. Run ~/.codex/bin/check-mcps when MCP health affects the task.
  4. Run ruby scripts/validation_report.rb for release/audit/process work. Add --release-checklists only when you need the deep all-app artifact checklist; the default report is the cheaper process/release verdict.
  5. Use the Mac Mini for SaneApps inspection, build, test, screenshots, and runtime verification unless the Mini is unavailable or the user explicitly approves a local exception.

Read the full file on GitHub · 365 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. 3d ago First seen · 365 lines · 4,303 tokens per session scan B 2933ee089c67

Subscribe to this mod's changes

SaneProcess AGENTS.md is an instructions file published in the GitHub repository sane-apps/SaneProcess (11 stars, last pushed 11d ago), licensed MIT. It adds 4,303 tokens to every session, about $0.0215 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

AI Safetycircuit-breakerdeveloper-toolslinuxmacosprocess-management
Related

Other instructions, from other repositories

microsandbox AGENTS.md

AGENTS.md instructions for superradcompany/microsandbox, covering agents.md, scope, project map, design principles and backward compatibility review.

superradcompany/microsandbox · 3,652 tokens

warp AGENTS.md

AGENTS.md instructions for warpdotdev/warp, covering agents.md, development commands, build and run, running with local warp-server and connect to server on default port 8080.

warpdotdev/warp · 4,233 tokens

terax-ai AGENTS.md

AGENTS.md instructions for crynta/terax-ai, a project described as: Lightweight (7MB) Terminal-first AI-native dev workspace.

crynta/terax-ai · 3 tokens

swift-tui AGENTS.md

Instructions for SwiftTUI/swift-tui, covering agents.md, build & test commands, architecture (one-page summary), development guidelines and code style.

SwiftTUI/swift-tui · 2,410 tokens

best-claude-hud AGENTS.md

Instructions for GaoSSR/best-claude-hud, covering project agent instructions and release work.

GaoSSR/best-claude-hud · 215 tokens

dotfiles AGENTS.md

Instructions for sebastienrousseau/dotfiles, covering project overview, key commands, repository layout, chezmoi naming conventions and conventions.

sebastienrousseau/dotfiles · 1,159 tokens