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/payloadcms/payload/triagegit clone --depth 1 https://github.com/payloadcms/payloadWhat 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 | $0.00025 | $0.00769 |
| Opus 5 | $0.00013 | $0.00385 |
| Sonnet 5 | $0.00005 | $0.00154 |
| Haiku 4.5 | $0.00003 | $0.00077 |
Grade A, and why
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 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Triage GitHub Issue
Quickly triage GitHub issues to determine validity and identify where the issue exists in code. Do not write code during triage.
Process
Step 1: Validate & Fetch
- Check if
$ARGUMENTSprovided - if missing, ask user and stop - Create TodoWrite with: Fetch and validate issue data | Investigate codebase | Analyze validity and generate report | Offer next steps
- Fetch issue data:
gh issue view $ARGUMENTS --json author,title,number,body,comments,labels,url - If command fails: Inform user and stop
- Extract title, body, comments, labels, state, URL
- Verify issue has sufficient info to investigate
Step 2: Investigate
- Use Task tool with subagent_type=Explore to examine relevant parts of codebase
- Think step by step through the code paths involved until you understand the relevant files, functions, and logic
- Focus on understanding the problem space before judging validity
Step 3: Analyze & Report
- Think step by step about whether this issue is valid - be critical and consider alternative explanations
- Determine verdict: Valid | Invalid | Needs Info
- Determine confidence: High | Medium | Low
- If valid: Think deeply about the root cause before proposing fix direction
- Generate findings using output structure below
- Auto-save to
.claude/artifacts/triage-<issue-number>.md - Present findings to user
Step 4: Offer Next Steps
Use AskUserQuestion with multiSelect: true:
"What would you like to do next?"
- Create failing test - Write integration test that reproduces the issue
- Create resolution plan - Generate full plan using
/superpowers:write-plan - Done for now - End triage
If user selects test: Write an integration test that reproduces the issue.
If user selects plan: Use /superpowers:write-plan to create detailed implementation plan.
Output Structure
# Triage: #<issue-number> - <title>
**Verdict:** Valid | Invalid | Needs Info
**Confidence:** High | Medium | Low
## Problem
1-2 sentences on what's broken and why.
## Reproduction
Steps to reproduce from investigation:
1. ...
2. ...
## Code Locations
- `path/file.ts:123` - what's here
- `path/other.ts:456` - related
## Fix Direction
Brief hints on potential approach (not full plan):
- Consider X
- May need to change Y
## Issue Link
<url>
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 · 109 lines · 25 tokens per session scan A 730d5a7414f1
triage is a command published in the GitHub repository payloadcms/payload (44,499 stars, last pushed 3d ago), licensed MIT. It adds 25 tokens to every session and 769 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 2026-08-30.
Other commands, from other repositories
sonicjs-pr-maker
You are a specialized agent that creates Pull Requests for SonicJS, monitors CI/CD pipelines, analyzes failures, and automatically fixes issues including E2E test failures.
sonicjs-release-announcement
You are a specialized agent that creates compelling release announcements for SonicJS across multiple platforms. Your primary responsibilities are.
sonicjs-blog-image
Generate professional blog post images using OpenAI's DALL-E API for the topic: $ARGUMENTS.
sonicjs-fullstack-dev
You are an expert full stack developer agent for SonicJS, a modern headless CMS built for Cloudflare's edge platform. You specialize in building high-quality, well-tested features with a systematic approach.
sonicjs-pr-fixer
You are a specialized agent that helps fix and merge problematic PRs in the SonicJS repository. This includes PRs from forks that need cherry-picking, Dependabot PRs that need e2e tests enabled, and any PR that needs fixes before merging.
sonicjs-seo
You are an SEO expert agent for SonicJS, a modern headless CMS built for Cloudflare's edge platform. Your goal is to help SonicJS rank for relevant keywords and grow organic traffic through legitimate, high-quality content strategies.