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/inkatze/planwright/buildernpx skills add inkatze/planwright --skill buildergit clone --depth 1 https://github.com/inkatze/planwrightWhat 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 | $0.00100 | $0.02489 |
| Opus 5 | $0.00050 | $0.01244 |
| Sonnet 5 | $0.00020 | $0.00498 |
| Haiku 4.5 | $0.00010 | $0.00249 |
Grade A, and why
builder 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.
How it starts
The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/builder
The engineering builder of the planwright pipeline (REQ-G1.2, D-15): the mechanism that gives a project the quality floor a principal engineer would set up — the formatter, the linters, the test runner, the secret scan, the commit and CI gates — by detecting the stack and applying the guards that stack warrants, so no human re-decides them each time. Its harder job is the inverse: recognizing the decisions that look mechanical but are architecture-defining, and escalating those instead of stamping a default (REQ-G1.3, D-16).
The builder is both a standalone skill (point it at a project to audit or set up its guards) and a hook the authoring and execution skills call into (the lifecycle wiring below). It recommends and applies; it never merges, never marks a PR ready, and never auto-defaults a load-bearing decision.
Doctrine
This skill is procedure, not doctrine. Resolve these rule docs via the
rule-doc resolution convention (scripts/resolve-rule-doc.sh <doc-name>
under the resolved planwright root, or the documented
PLANWRIGHT_ROOT/CLAUDE_PLUGIN_ROOT chain); the doctrine manifest below
marks which load at run start and which load at point of use (the escalation,
adoption, and interactive branches). Their definitions govern wherever this
skill names a concept:
guard-catalog— the normative core catalog: guard categories, the entry format, breadth dimensions, the extension model, and the dogfood contract. Its machine view isconfig/guard-catalog.yaml, read byscripts/builder-guards.sh.engineering-decisions— the decision ladder (idiom → tooling → mature-project research) and the no-flattening rule the escalation step applies.decision-domains— the catalogued stake-bearing domains and their triggers; what the builder escalates rather than auto-applies.finding-categorizationandgate-wiring— the buckets, the hard-disqualifier zones, and theGATE(when: …)deferral mechanism an escalated decision routes into.research-rigor— the mature-project comparison and new-dependency triggers that fire when a guard or tool is being adopted.proportionality— guard rigor scales with stake and reversibility; any scoping or departure is declared, never silent.interaction-style— governs the recommend/confirm exchanges when run interactively.
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.
- yesterday First seen · 196 lines · 100 tokens per session scan A cc21db5d0aa9
builder is a skill published in the GitHub repository inkatze/planwright (3 stars, last pushed 4d ago), licensed MIT. It adds 100 tokens to every session and 2,489 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
good-first-issue-batch
File a batch of contributor-ready GitHub issues from the seeds backlog, re-verifying every candidate against HEAD first so no dead issue reaches a contributor. Activate for prompts like "file some good first issues", "open a batch of GFIs", "publish backlog issues to GitHub", "find contributor-ready work", or after an…
seeds-issue-audit
Audit and triage open Seeds (sd) issues — find which can be closed, auto-close high-confidence completed ones, and report borderline cases. Activate for prompts like "audit open issues", "which seeds issues can be closed", "clean up the issue tracker", "triage the seeds backlog".
os-eco-dep-sync
Bump warren onto the latest published @os-eco/ versions across package.json + bun.lock and the Dockerfile CLI pins, then run the gates and open a PR. Use when checking if warren is on the newest burrow/plot/canopy/seeds/mulch/sapling.
release
Prepare, cut, and verify a warren release — tracker audits, version bump, CHANGELOG curation, ROADMAP update, push, then watch the pipeline through to published artifacts.
create-coordclaw-team
A Skill for creating a CoordClaw multi-agent collaborative team. Through an 8-step standardized process, from requirement gathering to team validation, rapidly build a complete AI team.
write-file
Replaces OpenClaw built-in write tool for all plain text writing, providing.