deployplan AGENTS.md

Repository instructions for deployplan, a tool for putting an app online and keeping it running. They guide an agent through inspecting the project, checking needed services, deploying, viewing logs, and rolling back.

In plain words
What is it for?
Use them to deploy an app, keep it running, check its status, investigate failures, manage services, attach an existing domain, or undo a deployment.
Why use it?
They give the agent a defined deployment process for an app owner who may not understand hosting vendors or infrastructure choices.

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/jsuncar/deployplan/agents-md
Clone the repo
git clone --depth 1 https://github.com/jsuncar/deployplan

Made for: Codex, OpenCode.

Per session 240 This file is loaded in full into every session.
When invoked 240 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 $0.00240 $0.00240
Opus 5 $0.00120 $0.00120
Sonnet 5 $0.00048 $0.00048
Haiku 4.5 $0.00024 $0.00024

Measured yesterday against content hash 864fe4ae7a23, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

deployplan 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 yesterday.

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 · 15 lines

What it actually says

deployplan

You are operating a citizen developer’s app. They own the git repo. They do not understand vendors. They said deploy, or keep it up.

Use the deployplan MCP (inspect_repo, interview_questions, list_required_services, propose_plan, quote_plan, apply_plan, stop, status, logs, events, rollback). list_required_services is always / workload / optional / Docker-live. apply_plan starts Docker services on this machine. Read docs/SERVICES.md.

Read skills/deploy-plan/SKILL.md and follow it.

deployplan is open source and not paid. Default apply path is the deployplan bundle on one account. External platforms in catalog/platforms.yaml are escape hatches for people who already use those vendors. Do not open a signup menu.

Human actions allowed: attach a domain they already own, open the URL. Human actions forbidden: ask them to pay, vendor signup, paste email, paste magic links, pick Vercel vs Supabase.

When something fails, call logs and events. The inbox is not a pager.

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. yesterday First seen · 15 lines · 240 tokens per session scan A 864fe4ae7a23

Subscribe to this mod's changes

deployplan AGENTS.md is an instructions file published in the GitHub repository jsuncar/deployplan (0 stars, last pushed 4d ago), licensed MIT. It adds 240 tokens to every session, about $0.0012 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 2026-08-31.