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/allisoneer/agentic_auxilaryWrote 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/allisoneer/agentic_auxilary/review_pr_comments)<a href="https://agentmods.dev/commands/allisoneer/agentic_auxilary/review_pr_comments"><img src="https://agentmods.dev/badge/commands/allisoneer/agentic_auxilary/review_pr_comments/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/allisoneer/agentic_auxilary/review_pr_comments"><img src="https://agentmods.dev/badge/commands/allisoneer/agentic_auxilary/review_pr_comments.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 | $0.00020 | $0.02590 |
| Opus 5.5 | $0.00008 | $0.01036 |
| Sonnet 5.5 | $0.00004 | $0.00518 |
| Haiku 4.5 | $0.00002 | $0.00259 |
Grade A, and why
review_pr_comments 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 — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Default behavior (no args):
- Fetch all unresolved comments on the current PR
- Triage all threads (
actionable,question,context,nit) with severity - Spawn 1 sub-agent per actionable or question thread for deep analysis
- Assess nits inline (
validity,effort,worth_addressing) without sub-agents - Write a versioned artifact with all threads analyzed and nits categorized
- Present an overview summary in the assistant response with categorized comments
The user then decides what to do: fix issues, add TODOs, send replies, investigate further, and so on. Do NOT proactively draft replies in the user-facing response or suggest sending them — let the user steer.
Keep instructions lean. The system prompt already covers tool mechanics.
<workflow_contract>
- Follow all 9 steps in order.
- Infer intent from
<userMessage>and use smart defaults when the request is mostly clear. - Fetch all relevant comment threads before final triage or conclusions.
- Use sub-agents for deeper analysis where warranted, but keep nit and context assessment lightweight unless the user asks for more.
- All threads must be evaluated; the difference is analysis depth, not whether they are analyzed.
- Write a versioned artifact before giving the final overview.
- Do not call
tools_gh_add_comment_replyunless the user explicitly asks for a reply. </workflow_contract>
<step_1>
Step 1: Interpret Intent
- Infer user intent from
<userMessage>. - If the user did not specify scope, default to the current PR, unresolved comments only, and
comment_source_type=all. - Recognize intent modifiers such as:
just triageanalyze everythinginclude resolvedhumans onlyorrobots onlypr 123only questionsoronly actionableskip nitshigh severity only
- Ask a clarifying question only if the requested scope is truly ambiguous.
- State any default assumptions clearly in the user-facing summary.
</step_1>
<step_2>
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 · 258 lines · 20 tokens per session scan A 66d12010c2f9
review_pr_comments is a command published in the GitHub repository allisoneer/agentic_auxilary (79 stars, last pushed 6d ago), licensed MIT. It adds 20 tokens to every session and 2,590 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-08.
Other commands, from other repositories
refactor
Systematic code refactoring with smart scope detection.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
init
Install the formatters this repository needs, with every command visible before it runs.
spec-trace-requirements
You are verifying that implementation changes trace back to specification requirements.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
boot
Start a new PromptKit prompt assembly session (alias for /bootstrap).