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.
npx agentmods add skills/bananasjim/openplan-skill/openplan-autonpx skills add BANANASJIM/openplan-skill --skill openplan-autogit clone --depth 1 https://github.com/BANANASJIM/openplan-skillWrote 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/skills/bananasjim/openplan-skill/openplan-auto)<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>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 | $0.00139 | $0.01404 |
| Opus 5 | $0.00069 | $0.00702 |
| Sonnet 5 | $0.00028 | $0.00281 |
| Haiku 4.5 | $0.00014 | $0.00140 |
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.
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
INIT: read request and local instructions.CLASSIFY: choose primary mode and surfaces.EVIDENCE: collect minimal durable evidence.DECIDE_ROUTE: bounded action, align, research, test, docs-init, review, garden, record proposal, handoff, HTML brief, or block.EXECUTE_SAFE: perform read-only work or explicitly authorized writes inside scope.VERIFY: run the proportional test, review, garden, or evidence check for the artifact touched.RECORD: propose durable memory/docs updates only when warranted.HANDOFF: write or emit a minimal continuation snapshot when work is long-running, cross-agent, blocked, or risky.REPORT: summarize scope, evidence, actions, decisions needed, next safe action, and residual risk.STOP: stop at the human decision boundary.
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.
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.
- 4d ago First seen · 134 lines · 139 tokens per session scan A 87b403750cda
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.
Other skills, from other repositories
nhk-bootstrap
Bootstrap an NHK workspace when first-time setup is needed or any required instruction, routing, planning, governance, or archive surface is missing.
nhk-upkeep
Repair NHK drift when an established workspace's instruction, routing, planning, governance, archive index, or tracking descriptions no longer match reality.
nhk-archive
Archive one completed NHK workstream when the human has explicitly approved its active-to-archive transition.
welcome-to-nhk
Route NHK work when dependency readiness, instruction topology, foundation state, or lifecycle stage is unresolved.
scribe-integration
How to use Scribe MCP tools correctly — logging, docs, topology, bugs, file reading, search.
scribe-onboarding
Install and connect Scribe MCP — pip install, one-command Postgres bootstrap, host/plugin projection, and first-bind verification.