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-docs-initnpx skills add BANANASJIM/openplan-skill --skill openplan-docs-initgit clone --depth 1 https://github.com/BANANASJIM/openplan-skillWhat 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 | $0.00090 | $0.01351 |
| Opus 5 | $0.00045 | $0.00675 |
| Sonnet 5 | $0.00018 | $0.00270 |
| Haiku 4.5 | $0.00009 | $0.00135 |
Grade A, and why
openplan-docs-init 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 2d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenPlan Docs Init
Use this after $openplan-core and usually after $openplan-align when a project needs an initial governed documentation surface before agents start generating durable docs.
Core Principle
Document generation begins with authority and provenance, not with a pile of files. Generated docs must not present agent assumptions as human intent.
When To Use
Use this skill when asked to:
- initialize an OpenPlan-style docs repo;
- add OpenPlan-style documentation governance to an existing code repo;
- create a minimal document map before generating project docs;
- seed needs snapshots, decision records, templates, or planning docs;
- prepare memory/docs for future Codex, Claude Code, or subagent sessions.
Do not use it for ordinary documentation edits after the document structure already exists. Use $openplan-record and $openplan-garden for that.
Init Flow
- Identify the target surface:
- docs repo;
- code repo;
- single-repo project;
- temporary teaching/reporting surface.
- Identify the documentation root:
- explicit user-provided path;
- existing project convention;
.openplan/when docs should live inside a code repo without mixing with product docs;docs/or repo root when that is the project convention;- a separate docs repo or absolute path when provided.
- Identify authority sources:
- explicit human goal/intent;
- existing docs/design/ADR files;
- code evidence;
- prior handoff or needs snapshot;
- agent inference.
- Decide the minimum document map needed for the next phase.
- Before creating durable docs, state:
- docs root;
- what will be generated;
- which source backs each file;
- what is inferred or pending confirmation;
- whether the file is source of truth, draft, handoff, review, or disposable.
- Generate only the smallest useful scaffold unless the user explicitly asks for a broader docs package.
- Record an explicit human decision, or propose/request a decision record, when initialization creates or changes durable design/governance.
- Seed a needs snapshot when the human goal/intent or project direction must survive across agents or sessions.
- Run
$openplan-gardenafter broad generation and$openplan-recordfor durable memory/docs updates. - Use
$openplan-researchfirst when the docs scaffold depends on facts not already backed by local durable context.
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.
- 2d ago First seen · 139 lines · 90 tokens per session scan A 907433164dec
openplan-docs-init is a skill published in the GitHub repository BANANASJIM/openplan-skill (4 stars, last pushed 3mo ago), licensed MIT. It adds 90 tokens to every session and 1,351 once invoked, about $0.0005 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.