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/capture_pr_comments_openai)<a href="https://agentmods.dev/commands/allisoneer/agentic_auxilary/capture_pr_comments_openai"><img src="https://agentmods.dev/badge/commands/allisoneer/agentic_auxilary/capture_pr_comments_openai/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/capture_pr_comments_openai"><img src="https://agentmods.dev/badge/commands/allisoneer/agentic_auxilary/capture_pr_comments_openai.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 | $0.00019 | $0.01826 |
| Opus 5.5 | $0.00008 | $0.00730 |
| Sonnet 5.5 | $0.00004 | $0.00365 |
| Haiku 4.5 | $0.00002 | $0.00183 |
Grade A, and why
capture_pr_comments_openai 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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This command is intentionally low-judgment. It should document what exists right now, not decide what to fix, what to research, or what to reply.
<workflow_contract>
- Follow all 8 steps in order.
- Default to the current PR, all comment sources, and unresolved comments only unless the user specifies otherwise.
- Exhaust pagination and gather bounded code snapshots before writing the final artifact.
- Treat the parent comment ID as the only safe inferred thread identifier unless the tool explicitly exposes something better.
- If pagination state appears lost or restarted, restart intentionally and document that fact instead of guessing.
- Use direct bounded
readwindows for anchored code snapshots; do not use sub-agents for this by default. - Write a versioned artifact before the final response.
- Do not call
tools_ask_agent,tools_gh_add_comment_reply, planning workflows, or implementation workflows from this command. </workflow_contract>
<step_1>
Step 1: Interpret Intent and Scope
- Infer scope from
<userMessage>. - Support these common modifiers when the user mentions them:
pr 123or another explicit PR numberinclude resolvedhumans onlyrobots onlyall comments
- If the user does not narrow scope, assume:
- current PR
comment_source_type=allinclude_resolved=false
- Ask a clarifying question only if the PR cannot be determined and the user did not provide enough information to choose one responsibly.
- Record any assumptions for the final response and artifact header.
</step_1>
<step_2>
Step 2: Identify the PR Conservatively
- If the user provided
pr_number, use it. - Otherwise call
tools_gh_get_commentswithoutpr_numberand let the tool attempt autodetection. - If autodetection fails, call
tools_gh_get_prs, follow the tool-visible pagination cues, and stop when the tool says completion. - If multiple PR candidates remain and you still cannot choose responsibly, ask the user to choose.
- Treat autodetection as a convenience, not a guarantee.
- Use GitHub tool output as the authoritative source for PR number, repo, and PR 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.
- 1mo ago First seen · 200 lines · 19 tokens per session scan A 4996cc482a9b
capture_pr_comments_openai is a command published in the GitHub repository allisoneer/agentic_auxilary (79 stars, last pushed 6d ago), licensed MIT. It adds 19 tokens to every session and 1,826 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-08.
Other commands, from other repositories
speckit.spex.submit
Push and create PR for team review, with optional watch mode for CI monitoring.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
factory
Linha de montagem multi-agente (Software Factory) — spec-writer → builder em worktree isolado → 4 revisores paralelos (Security, Code, UI, UX) → approver com gate de risco e dashboard visual.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.
release-tag
Create and push a version tag after a release PR has been merged.