Borrowing it
Nothing to install: this file belongs to sane-apps/SaneProcess. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sane-apps/SaneProcess/main/AGENTS.mdgit clone --depth 1 https://github.com/sane-apps/SaneProcessWrote 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.
[](https://agentmods.dev/instructions/sane-apps/saneprocess/agents-md)<a href="https://agentmods.dev/instructions/sane-apps/saneprocess/agents-md"><img src="https://agentmods.dev/badge/instructions/sane-apps/saneprocess/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.
<a href="https://agentmods.dev/instructions/sane-apps/saneprocess/agents-md"><img src="https://agentmods.dev/badge/instructions/sane-apps/saneprocess/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.03598 | $0.03598 |
| Opus 5.5 | $0.01439 | $0.01439 |
| Sonnet 5.5 | $0.00720 | $0.00720 |
| Haiku 4.5 | $0.00360 | $0.00360 |
Grade B, and why
SaneProcess AGENTS.md scanned grade B 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 1mo 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. How it starts
The opening of the file, as written. The whole thing — 312 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; the full runbook lives in DEVELOPMENT.md, ARCHITECTURE.md,
DEVELOPER_SETUP.md, templates/RELEASE_SOP.md, and scripts/.
Regular daily work is Grok, Grokbot, and Cursor (native ~/.grok/hooks and
~/.cursor/hooks.json; keep Codex/Claude adapters working). Do not send
regular jobs to OpenAI or Anthropic unless the owner asks.
Speak plainly and briefly, in singular voice (I, me, my).
What Belongs Here
Keep only instructions an agent must know before hooks or wrappers can help;
point at enforcement instead of duplicating policy. Enforcement:
scripts/hooks/ (launch, build-route, release, email, GitHub, tracking,
session-end, security, visual-proof, GUI-feedback, completion gates);
scripts/SaneMaster.rb + scripts/sanemaster/ (workflows);
validation_report.rb, process_eval, sop_review, near_miss_review,
tests (process evidence); handoff, research cache, file memory, Mini
AgentMemory (context; Serena is code-navigation only).
Session Start
Tiny read-only answers need only the relevant file/command surface. For code, audit, release, support, payment, App Store, automation, UI/runtime, or multi-file work:
- Read
SESSION_HANDOFF.md. - Read relevant file memory and the active skill registry; query shared
context with AgentMemory
memory_recallormemory_smart_search. - Run
~/.grok/bin/check-mcpsorruby scripts/SaneMaster.rb tool_discovery --query "mcp health"when MCP health affects the task. - Run
ruby scripts/validation_report.rbfor release/audit/process work (--release-checklistsonly for the deep all-app artifact checklist). - 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.
Session End
When code, tooling, docs, policy, support, release, or UI/runtime behavior changed:
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.
- 1mo ago Changed · -53 lines · -705 tokens per session 21f1982903e2
- 1mo ago First seen · 365 lines · 4,303 tokens per session scan B 2933ee089c67
SaneProcess AGENTS.md is an instructions file published in the GitHub repository sane-apps/SaneProcess (11 stars, last pushed 25d ago), licensed MIT. It adds 3,598 tokens to every session, about $0.0144 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.