A command for drafting comments on GitHub issues and pull requests, where people discuss bugs and proposed code changes. It can also publish an approved comment.

Use it to write status updates, decisions, questions, review comments, or closing messages for GitHub threads.

It helps produce stakeholder-readable updates with correct links while keeping publication under the user's control by default.

comment — Command by koolamusic

Install

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.

agentmods

npx agentmods add commands/koolamusic/claudefiles/comment

Clone the repo

git clone --depth 1 https://github.com/koolamusic/claudefiles

Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 988 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00040	$0.00988
Opus 5	$0.00020	$0.00494
Sonnet 5	$0.00008	$0.00198
Haiku 4.5	$0.00004	$0.00099

Measured 2d ago against content hash e7f3fb398b7e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

comment 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 2d 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.

plugins/jira/commands/comment.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Draft (and optionally post) a GitHub comment. Voice and linking rules live in ${CLAUDE_PLUGIN_ROOT}/templates/comment/GUIDE.md. Public/internal boundary: ${CLAUDE_PLUGIN_ROOT}/templates/author-conventions.md.

Parse the input

$ARGUMENTS may include:

--repo owner/name — target repo (default: gh repo view --json nameWithOwner -q .nameWithOwner from cwd)
--issue N or --pr N — target thread (required unless obvious from conversation)
Shape hint (optional): --close | --decide | --status | --ask | --review
--post — actually publish via gh; without it, only draft and show the user
Remaining free text — the substance of the comment (decision, evidence, ask)

If the target (--issue / --pr) or the substance is missing and cannot be inferred from the conversation, use AskUserQuestion once. Do not invent a decision.

Steps

Read the guides (every run):
- ${CLAUDE_PLUGIN_ROOT}/templates/comment/GUIDE.md
- ${CLAUDE_PLUGIN_ROOT}/templates/author-conventions.md
Resolve the thread. Fetch enough context to avoid writing past the current state:
```
gh issue view N --repo OWNER/REPO --json title,state,body,comments
# or
gh pr view N --repo OWNER/REPO --json title,state,body,comments,commits
```
Skim the latest comments. Do not contradict a newer disposition without acknowledging it.
Resolve permalinks before drafting.
- For every file/line you cite: get a commit SHA (git rev-parse HEAD in that repo, or the SHA named in evidence) and build: https://github.com/OWNER/REPO/blob/<sha>/<path>#L<start>-L<end>
- Same-repo issues/PRs → #N. Cross-repo → owner/repo#N.
- Prefer SHA-pinned code links for evidence; branch tips only when you mean "as of this tip".
Draft the comment per GUIDE:
- Lead with the plain situation (1–2 sentences a stranger can parse)
- Evidence with clickable links
- One clear outcome (status / decision / ask)
- Strip: hostnames, vendor box names, .jira/ paths, decision IDs, wave labels, worktree paths, AI trailers
- Feature PRs: Refs #N, never Closes (author-conventions)

Read the full file on GitHub · 79 lines

Changes

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.

2d ago First seen · 79 lines · 40 tokens per session scan A e7f3fb398b7e

Subscribe to this mod's changes

comment is a command published in the GitHub repository koolamusic/claudefiles (132 stars, last pushed 3d ago), licensed MIT. It adds 40 tokens to every session and 988 once invoked, about $0.0002 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.

Git and workflow

comment

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Parse the input

Steps

What this file has done since we first saw it

Other commands, from other repositories

git

checklist

clarify

specify

analyze

converge