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.
git clone --depth 1 https://github.com/rjmurillo/ai-agentsWrote 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/rjmurillo/ai-agents/pr-comment-triage)<a href="https://agentmods.dev/commands/rjmurillo/ai-agents/pr-comment-triage"><img src="https://agentmods.dev/badge/commands/rjmurillo/ai-agents/pr-comment-triage/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/commands/rjmurillo/ai-agents/pr-comment-triage"><img src="https://agentmods.dev/badge/commands/rjmurillo/ai-agents/pr-comment-triage.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 | $0.00000 | $0.01007 |
| Opus 5.5 | $0.00000 | $0.00403 |
| Sonnet 5.5 | $0.00000 | $0.00201 |
| Haiku 4.5 | $0.00000 | $0.00101 |
Grade A, and why
pr-comment-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 1mo 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Comment Triage
Analyze all comments on this pull request and provide a structured triage decision for each.
Your Task
- Review each comment from bots (gemini-code-assist, copilot-pull-request-reviewer, coderabbitai) and humans
- Classify each comment by type and priority
- Determine the appropriate action for each
- Return structured JSON that can be parsed by automation
Classification Rules
| Classification | Description | Action |
|---|---|---|
quick-fix |
Single file, clear fix, no architecture impact | Implement immediately |
standard |
Needs investigation, may affect multiple files | Implement with analysis |
strategic |
Questions architecture or approach (why, not how) | Reply with rationale |
wontfix |
Invalid, out of scope, or disagree with principle | Reply declining |
question |
Needs clarification before proceeding | Reply asking for details |
stale |
Already addressed or superseded | Mark resolved |
Priority Levels
| Priority | Description |
|---|---|
critical |
Blocks merge - security, correctness, or breaking change |
major |
Should fix before merge - significant improvement |
minor |
Nice to have - can address in follow-up |
Output Format
Your ENTIRE response must be a single JSON object. NO other text.
- Start your response with
{and end with} - Do NOT wrap JSON in markdown code fences
- Do NOT include explanations before or after the JSON
Required JSON Schema
| Field | Type | Required | Description |
|---|---|---|---|
comments |
array | Yes | One entry per comment analyzed |
comments[].id |
number | Yes | Comment ID from GitHub API |
comments[].author |
string | Yes | Username of commenter |
comments[].file |
string | When available | File path the comment references |
comments[].line |
number | When available | Line number the comment references |
comments[].classification |
string | Yes | One of: quick-fix, standard, strategic, wontfix, question, stale |
comments[].priority |
string | Yes | One of: critical, major, minor |
comments[].action |
string | Yes | One of: implement, reply, resolve |
comments[].summary |
string | Yes | Brief description of the issue |
comments[].resolution |
string | Yes | Specific fix or response |
summary |
object | Yes | Counts by classification |
recommendation |
string | Yes | Human-readable summary of actions |
verdict |
string | Yes | PASS or WARN |
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.
- 1mo ago First seen · 94 lines · 0 tokens per session scan A f43681ac8a8f
pr-comment-triage is a command published in the GitHub repository rjmurillo/ai-agents (49 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,007 tokens. 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 2026-09-06.
Other commands, from other repositories
review-deep
Review change vs spec, plan, code quality heuristics, and repo rules; append remediation phase if needed.
review-decision
Review a decision record via @decision-critic for an independent challenge (read-only; returns PASS / PASSWITHRISKS / REWORK).
review-remote
Review open PR/MR and publish findings.
apply-review-feedback
Classify and apply accepted PR/MR review feedback.
pr
Create/update PR/MR title and description.
upload-report
Run automation and upload or verify Katalon Platform reports for Katalon Studio/KRE, JUnit XML, and Playwright reports. Use when you need to combine Katalon MCP project/result discovery with Katalon CLI execution, Katalon Report Uploader, or @katalon/playwright-reporter; configure report folders, report types…