openplan-auto

openplan-auto is a skill for Claude Code, Codex from BANANASJIM/openplan-skill. It costs 139 tokens per session (1,404 once invoked), scanned A, original, MIT.

An automatic workflow guide for OpenPlan-style coding-agent work, including inspection, alignment, research, testing, review, documentation checks, and handoff.

In plain words
What is it for?
Use it for unattended or low-interaction workflows that need evidence gathering, proportional checks, reports, proposals, handoffs, or temporary HTML summaries.
Why use it?
It lets an agent handle routine stages automatically while stopping when a person must decide scope, risk, approval, or whether to accept a change.

Skill for Claude CodeCodex

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 skills/bananasjim/openplan-skill/openplan-auto
Any agent
npx skills add BANANASJIM/openplan-skill --skill openplan-auto
Clone the repo
git clone --depth 1 https://github.com/BANANASJIM/openplan-skill

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for openplan-auto

README.md
[![agentmods](https://agentmods.dev/badge/skills/bananasjim/openplan-skill/openplan-auto.svg)](https://agentmods.dev/skills/bananasjim/openplan-skill/openplan-auto)
Your own site
<a href="https://agentmods.dev/skills/bananasjim/openplan-skill/openplan-auto"><img src="https://agentmods.dev/badge/skills/bananasjim/openplan-skill/openplan-auto.svg" alt="Measured on agentmods" height="20"></a>
Per session 139 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,404 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00139 $0.01404
Opus 5 $0.00069 $0.00702
Sonnet 5 $0.00028 $0.00281
Haiku 4.5 $0.00014 $0.00140

Measured 4d ago against content hash 87b403750cda, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

openplan-auto 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 4d 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.

skills/openplan-auto/SKILL.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenPlan Auto

Use this as the orchestration layer for unattended or low-interaction workflows.

Core Rule

Auto mode can gather evidence, classify, review, summarize, and prepare proposals. It cannot make human-owned decisions, accept risk, approve changes, or silently mutate durable goal/intent.

Skill Order

Default chain:

core -> operate -> (align/research if needed) -> action/test/review/garden -> record proposal -> handoff -> html brief

Use only the stages needed.

Stage Skill Auto Can Do Must Stop For
Principles $openplan-core Apply invariants Conflicting human/platform instruction
Startup $openplan-operate Load minimal context, choose mode Destructive or broad action
Alignment $openplan-align Infer safe route, ask limited questions only as the human-facing coordinator Scope/architecture/risk decision
Research $openplan-research Gather bounded evidence Turning findings into decisions
Test $openplan-test Choose proportional checks, prove regression coverage, report skipped checks Approval, merge/release, or risk acceptance
Review $openplan-review Read-only findings Approval or fixes
Garden $openplan-garden Semantic doc report Durable doc rewrite
Record $openplan-record Propose memory/docs updates Ambiguous durable goal/intent update
Docs Init $openplan-docs-init Initialize governed document generation Durable governance/design decision
Handoff $openplan-handoff Snapshot state None, unless it would assert unverified facts
HTML $openplan-html-brief Temporary human frontend Persisting or committing HTML

State Machine

  1. INIT: read request and local instructions.
  2. CLASSIFY: choose primary mode and surfaces.
  3. EVIDENCE: collect minimal durable evidence.
  4. DECIDE_ROUTE: bounded action, align, research, test, docs-init, review, garden, record proposal, handoff, HTML brief, or block.
  5. EXECUTE_SAFE: perform read-only work or explicitly authorized writes inside scope.
  6. VERIFY: run the proportional test, review, garden, or evidence check for the artifact touched.
  7. RECORD: propose durable memory/docs updates only when warranted.
  8. HANDOFF: write or emit a minimal continuation snapshot when work is long-running, cross-agent, blocked, or risky.
  9. REPORT: summarize scope, evidence, actions, decisions needed, next safe action, and residual risk.
  10. STOP: stop at the human decision boundary.

Read the full file on GitHub · 134 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 4d ago First seen · 134 lines · 139 tokens per session scan A 87b403750cda

Subscribe to this mod's changes

openplan-auto is a skill published in the GitHub repository BANANASJIM/openplan-skill (4 stars, last pushed 3mo ago), licensed MIT. It adds 139 tokens to every session and 1,404 once invoked, about $0.0007 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.