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 skills add inkatze/planwright --skill towergit clone --depth 1 https://github.com/inkatze/planwrightWrote 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/inkatze/planwright/tower)<a href="https://agentmods.dev/skills/inkatze/planwright/tower"><img src="https://agentmods.dev/badge/skills/inkatze/planwright/tower/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/skills/inkatze/planwright/tower"><img src="https://agentmods.dev/badge/skills/inkatze/planwright/tower.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 | $0.00096 | $0.05631 |
| Opus 5.5 | $0.00038 | $0.02252 |
| Sonnet 5.5 | $0.00019 | $0.01126 |
| Haiku 4.5 | $0.00010 | $0.00563 |
Grade A, and why
tower 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 5d 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 — 396 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/tower — the front door
/tower is the standing conversational session planwright is entered through
(REQ-A1.1): the operator says what they want in their own words, and the tower
decides per request how that work flies. Visual flight is specless work — an
isolated worker on its own branch, converging through review, landing a draft
PR or record whose audit record carries the trust. Instrument flight is the
spec pipeline. The names are the aviation analogy: visual rules when conditions are
clear enough to fly by what you can see, instrument rules when you file a plan
and trust the gauges (D-3). The tower never edits the repository itself — every
mutation is a flight (REQ-C1.6).
Doctrine
This skill is procedure, not doctrine; the rule docs below govern wherever it
names a concept. Resolve each via scripts/resolve-rule-doc.sh <doc-name>
under the resolved planwright root. A run-start doc that does not resolve halts the
session naming the doc and the chain consulted; a point-of-use doc that does
not resolve halts that step alone.
Doctrine manifest (machine-parseable, per doctrine/instruction-hygiene.md;
run-start loads before work begins, point-of-use at the named step):
Doctrine: run-start flight-rules Doctrine: run-start work-placement Doctrine: run-start interaction-style Doctrine: run-start tower-comms Doctrine: point-of-use spec-format (flight branch grammar; status lifecycle; the relay's spec path) Doctrine: point-of-use security-posture (data hygiene at every hand-off)
Invoking plugin scripts (worker-permission-ergonomics REQ-D1.1, D-7). Call
scripts/<name>.sh by the resolved literal absolute path, never
$VAR/scripts/<name>.sh — doctrine/plugin-script-invocation.md.
Values in commands. A branch name, flight id, or <spec> is checked
against its grammar (spec-format's) before it enters any command run or
offered; a <spec> must equal an existing specs/*/ basename; no match asks
the operator.
Session bring-up
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.
- 5d ago Changed · +8 lines 9fe17d344b29
- 9d ago Changed · +7 lines 47cf26530720
- 10d ago Changed · +5 lines a85dc86ffd54
- 12d ago Changed · +6 lines 24b7ef18cb39
- 18d ago Changed · +7 lines b79e463e1e23
- 19d ago Changed · +6 lines ba2053da2ffe
- 20d ago Changed · +11 lines a912f166a474
- 22d ago Changed · +1 lines fdd7c1bded64
- 23d ago First seen · 345 lines · 96 tokens per session scan A 20f43726ee75
tower is a skill published in the GitHub repository inkatze/planwright (5 stars, last pushed today), licensed MIT. It adds 96 tokens to every session and 5,631 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-26.
Other skills, from other repositories
prd-builder
Use to construct a complete Product Requirements Document for a mobile app from a vision file. Used primarily by the CPO agent. Triggers on requests to "write the PRD", "spec out the product", or as part of /app-plan.
brownfield-onboarding
Use when pointing the team at an EXISTING, already-built app instead of a blank project — detects the stack, reverse-engineers the as-built architecture, and classifies remediation work as safe-to-auto-fix vs risky-needs-approval. Triggered by /app-onboard, /app-audit, and by /app-run when it detects a non-empty app…
process-tiering
Use when sizing a ticket at planning time, and when calibrating how much review ceremony a diff needs. Maps the studio's existing XS/S/M/L/XL estimate to how much process a ticket carries — a one-line fix should not walk the same PRD-to-impl-spec pipeline as a multi-screen feature. Triggers from sprint-planner (at…
paperclip
Use for Paperclip-managed tasks and heartbeats: reading task context, delivering task documents or files, updating completion or blockers, coordinating or delegating work, and following company governance. Includes control plane API operations for assignments, comments, approvals, and routines.
paperclip-board
Manage a Paperclip company as a board member via chat. Use when the user wants onboarding, company or agent management, approvals, task monitoring, cost oversight, or work product review in the Paperclip control plane.
paperclip-distill
Use when an operation issue is a Paperclip cursor-window, distill, or backfill. Turn source-bundled Paperclip activity into wiki-insightful project standups, durable project pages, decisions, and history without asset dereferencing.