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 rp1-run/rp1 --skill arcade-collabgit clone --depth 1 https://github.com/rp1-run/rp1Wrote 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/rp1-run/rp1/arcade-collab)<a href="https://agentmods.dev/skills/rp1-run/rp1/arcade-collab"><img src="https://agentmods.dev/badge/skills/rp1-run/rp1/arcade-collab/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/rp1-run/rp1/arcade-collab"><img src="https://agentmods.dev/badge/skills/rp1-run/rp1/arcade-collab.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 | $0.00031 | $0.01527 |
| Opus 5 | $0.00015 | $0.00763 |
| Sonnet 5 | $0.00006 | $0.00305 |
| Haiku 4.5 | $0.00003 | $0.00153 |
Grade A, and why
arcade-collab 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arcade Collaboration
Process user feedback from the Arcade: annotations and direct file edits. Follow the loop below exactly, then return control to the calling gate.
1. Read Feedback
Fetch all open feedback for the current run:
rp1 agent-tools feedback read --run-id {RUN_ID} --status open
Parse the JSON response. It contains:
annotations[]: Open annotations with id, docId, artifactPath, content, anchor, status, author, replies, createdAt.edits[]: Pending file edits with docId, artifactPath, patch (unified diff).summary: Counts of totalAnnotations, totalEdits, and byArtifactType breakdown.
If both totalAnnotations and totalEdits are zero: No pending feedback. Return to the calling gate immediately. Do not produce any output about the feedback check.
2. Classify Feedback
Classify each feedback item by the artifact it targets:
| Artifact Pattern | Classification | Routing |
|---|---|---|
requirements.md |
Requirements feedback | Spawn feature-editor agent |
design.md, design-decisions.md |
Design feedback | Spawn feature-editor agent |
Code files (.ts, .tsx, .js, .jsx, .py, .rs, etc.) |
Code feedback | Apply fix directly |
| Other files or unanchored annotations | General feedback | Incorporate into context, acknowledge |
For annotations: classify based on artifactPath. If artifactPath is null (unanchored), classify as General.
For edits: classify based on artifactPath in the edit record.
3. Sort by Dependency Order
Process feedback in this strict order:
- Requirements feedback first (upstream changes may invalidate downstream artifacts)
- Design feedback second
- Code feedback third
- General feedback last
Within each category, process annotations before edits.
4. Act on Each Item
4.1 Requirements and Design Feedback (Annotations)
Route to the feature-editor agent with the annotation content as the edit description:
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 · 187 lines · 31 tokens per session scan A 98d5f1457148
arcade-collab is a skill published in the GitHub repository rp1-run/rp1 (38 stars, last pushed 3d ago), licensed Apache-2.0. It adds 31 tokens to every session and 1,527 once invoked, about $0.0002 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 2026-09-07.
Other skills, from other repositories
dream
Batch-execute SHIP-ready wishes overnight — pick wishes, orchestrate workers, review PRs, wake up to results.
at-zentao
Handle ZenTao (禅道) Bugs and Tasks end to end, including updating or writing back an item after code changes, managing Task status and hours, and reading linked Stories. Use for referenced ZenTao items, requirements, status changes, time entries, or post-implementation synchronization.
openspec-bulk-apply-change
Use when multiple active OpenSpec changes should be applied concurrently in isolated worktrees with delegated verification and no merge.
genie-orca-wish
Turn a brainstorm/design into an APPROVED-able wish whose Dispatch plan is the literal input to Orca tasks and Linear issues. High-reasoning pass: pre-decide everything so fast workers can execute without judgment calls.
honest-closeout
Close a task with a report a reviewer can trust — every acceptance line answered with evidence or a recorded blocking reason, human corrections credited to whoever made them, refuted hypotheses kept, background processes proven stopped, and the chat message copied verbatim from the report. Use when reporting work as…
close-the-gaps
Product Analyst session: fetches a ticket, loads project skills, explores affected code, asks gap-analysis questions one at a time, outputs Gherkin-format refined ticket. Use when refining a ticket before dev starts.