Routa is a workspace-based coordination platform for delivering software with multiple AI agents, keeping goals, tasks, sessions, traces, evidence, and review decisions visible on a shared board. It is intended for teams managing agent-assisted development across web and desktop applications. The catalogue contains skills and instructions for working with Routa's delivery workflows.
Borrowing it
Nothing to install: this file belongs to phodal/routa. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/phodal/routa/main/.claude/skills/issue-garbage-collector/SKILL.mdgit clone --depth 1 https://github.com/phodal/routaWrote 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/phodal/routa/issue-garbage-collector)<a href="https://agentmods.dev/skills/phodal/routa/issue-garbage-collector"><img src="https://agentmods.dev/badge/skills/phodal/routa/issue-garbage-collector/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/phodal/routa/issue-garbage-collector"><img src="https://agentmods.dev/badge/skills/phodal/routa/issue-garbage-collector.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Excessive Agency · line 106 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
- medium Excessive Agency · line 156 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 205 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00046 | $0.01879 |
| Opus 5 | $0.00023 | $0.00940 |
| Sonnet 5 | $0.00009 | $0.00376 |
| Haiku 4.5 | $0.00005 | $0.00188 |
Grade A, and why
issue-garbage-collector 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 9d 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 — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quick Start
# Phase 1: Run Python scanner (fast, free)
python3 .github/scripts/issue-scanner.py
# Phase 1: Get suspects only (for Phase 2 input)
python3 .github/scripts/issue-scanner.py --suspects-only
# Phase 1: JSON output (for automation)
python3 .github/scripts/issue-scanner.py --json
# Phase 1: Validation check (CI integration, exit 1 if errors)
python3 .github/scripts/issue-scanner.py --check
Harness Integration
- Repo-defined entry:
docs/harness/automations.ymlcontainsissue-gc-review - Harness surface:
settings/harness→Cleanup & Correction - Data source: the Harness automation view reads suspect data from
python3 .github/scripts/issue-scanner.py --suspects-only - Intended usage: review pending duplicate / stale / open-check suspects in Harness first, then decide whether to run the cleanup workflow below
Two-Phase Strategy (Cost Optimization)
Problem: Running deep AI analysis on every issue is expensive.
Solution: Two-phase approach:
- Phase 1 (Fast/Free) — Python script for pattern matching
- Phase 2 (Deep/Expensive) —
claude -ponly on suspects
┌─────────────────────────────────────────────────────────┐
│ All Issues (N files) │
│ ┌───────────────────────────────────────────────────┐ │
│ │ Phase 1: Python Scanner (.github/scripts/issue-scanner.py)│ │
│ │ - Filename keyword extraction │ │
│ │ - YAML front-matter validation │ │
│ │ - Same area + keyword overlap detection │ │
│ │ - Age-based staleness check │ │
│ │ → Output: Suspect list (M files, M << N) │ │
│ └───────────────────────────────────────────────────┘ │
│ ↓ │
│ ┌───────────────────────────────────────────────────┐ │
│ │ Phase 2: Deep Analysis (claude -p, only M files) │ │
│ │ - Content similarity │ │
│ │ - Semantic duplicate detection │ │
│ │ - Merge recommendations │ │
│ └───────────────────────────────────────────────────┘ │
└─────────────────────────────────────────────────────────┘
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.
- 9d ago First seen · 228 lines · 46 tokens per session scan A 701d6299495b
issue-garbage-collector is a skill published in the GitHub repository phodal/routa (1,810 stars, last pushed 26d ago), licensed MIT. It adds 46 tokens to every session and 1,879 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 2026-08-30.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
overleaf-sync
A two-way connection between a local paper folder and Overleaf, a web-based LaTeX editor for writing research papers. It lets you move changes between the local files and the shared Overleaf project.