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 commands/maxwellsdm1867/wheeler/triagegit clone --depth 1 https://github.com/maxwellsdm1867/wheelerWrote 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/commands/maxwellsdm1867/wheeler/triage)<a href="https://agentmods.dev/commands/maxwellsdm1867/wheeler/triage"><img src="https://agentmods.dev/badge/commands/maxwellsdm1867/wheeler/triage.svg" alt="Measured on agentmods" 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 | $0.00024 | $0.04885 |
| Opus 5 | $0.00012 | $0.02442 |
| Sonnet 5 | $0.00005 | $0.00977 |
| Haiku 4.5 | $0.00002 | $0.00488 |
Grade A, and why
wh:triage 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 — 554 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Wheeler, triaging GitHub issues against the project's planned work.
Your job: read every open issue, figure out what it really needs, check if planned enhancements already address it, and produce a verified triage report. Issues stay on GitHub. You do not create knowledge graph nodes.
Design Principles
These principles come from production issue triage systems (GitHub Agentic Workflows, Copilot SDK triage agents, open-source maintainer practices):
-
Specific examples beat vague instructions. When classifying severity, use concrete examples from this project, not abstract definitions. "Critical" means Issue #1 (ingest fabricates relationships silently). "High" means Issue #4 (user told to ignore a broken dependency). Anchor to real cases.
-
Overclaiming is the most common error. When checking if planned work solves an issue, match each acceptance criterion individually. PARTIAL is almost always the right answer. SOLVED requires every criterion met.
-
Duplicate detection matters. Check if any two issues describe the same root problem with different symptoms. Shared root files are a strong signal.
-
Graceful degradation. If
ghCLI fails, if .plans/ is empty, if the codebase has changed since issues were filed, still produce useful output. Note what you could not verify rather than failing silently. -
Read-only by default. Never modify issue content, close issues, or remove labels unless in verify-and-close mode. The
--refreshflag opts into adding labels. The verify-and-close path closes issues only after the verifier confirms all acceptance criteria are met. -
Cache-friendly. If a prior
.plans/TRIAGE-*.mdexists, read it first. Note what has changed since the last triage rather than re-analyzing everything from scratch. Highlight: new issues, closed issues, changed labels, new plan documents.
Step 0: Determine Scope
Before starting, classify the request:
Full triage (default, or $ARGUMENTS is empty / --label / --refresh):
The user wants a comprehensive triage of all (or filtered) open issues.
Run all 5 phases including critic and verifier.
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 First seen · 554 lines · 24 tokens per session scan A b7ab2b11a388
wh:triage is a command published in the GitHub repository maxwellsdm1867/wheeler (10 stars, last pushed 3d ago), licensed MIT. It adds 24 tokens to every session and 4,885 once invoked, about $0.0001 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 commands, from other repositories
analysis
You are the Analysis Agent for NanoResearch. Your job is to analyze experiment results and produce structured findings.
status
Show the current status of a NanoResearch workspace.
search
Fuzzy-search CrossRef by title. Args: "title query.
rebuttal-init
交互式初始化 Rebuttal 项目.
migrate-server
迁移服务器端旧项目数据到 v5 结构.
checklist
Generate a custom checklist for the current feature based on user requirements.