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 skills add dremonkey/agents-and-skills --skill glab-mr-line-commentgit clone --depth 1 https://github.com/dremonkey/agents-and-skillsWrote 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/skills/dremonkey/agents-and-skills/glab-mr-line-comment)<a href="https://agentmods.dev/skills/dremonkey/agents-and-skills/glab-mr-line-comment"><img src="https://agentmods.dev/badge/skills/dremonkey/agents-and-skills/glab-mr-line-comment/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/skills/dremonkey/agents-and-skills/glab-mr-line-comment"><img src="https://agentmods.dev/badge/skills/dremonkey/agents-and-skills/glab-mr-line-comment.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 | $0.00088 | $0.01969 |
| Opus 5 | $0.00044 | $0.00984 |
| Sonnet 5 | $0.00018 | $0.00394 |
| Haiku 4.5 | $0.00009 | $0.00197 |
Grade A, and why
glab-mr-line-comment scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Line-attached MR comments on GitLab via glab
When to use
The user asks you to post review feedback as inline comments on specific
lines of a GitLab MR diff. The deliverable is a DiffNote (rendered next
to the changed line in the MR diff view), not a DiscussionNote (rendered
in the MR-level activity feed).
The trap
The obvious approach is to use glab api with --field for each
parameter, including nested position[*] keys:
# DO NOT DO THIS — silently degrades to a DiscussionNote
glab api projects/$PID/merge_requests/$IID/discussions -X POST \
--field "body=$BODY" \
--field "position[base_sha]=..." \
--field "position[head_sha]=..." \
--field "position[new_path]=path/to/file.ts" \
--field "position[new_line]=42" \
...
GitLab's API accepts this request and returns 201, but the resulting
note has type: DiscussionNote and no position field. The form-encoded
position[*] keys are silently dropped on this endpoint. The comment
appears on the MR but is not attached to any line of the diff.
This failure mode is invisible until you actually look at the MR in a
browser or query the note back. glab mr note does not support diff
positions at all — only glab api does, and only with a JSON body.
The fix
Send the request as a JSON body with --input and an explicit
Content-Type header:
glab api projects/$PROJECT_ID/merge_requests/$MR_IID/discussions \
-X POST \
-H "Content-Type: application/json" \
--input /tmp/comment.json
Where /tmp/comment.json is:
{
"body": "...markdown...",
"position": {
"base_sha": "...",
"start_sha": "...",
"head_sha": "...",
"position_type": "text",
"new_path": "path/to/file.ts",
"old_path": "path/to/file.ts",
"new_line": 42
}
}
The response will have notes[0].type === 'DiffNote' and a populated
position object. If type is DiscussionNote, the position was
dropped — the comment is not line-attached.
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.
- 10d ago First seen · 226 lines · 88 tokens per session scan A 52d15feb4c68
glab-mr-line-comment is a skill published in the GitHub repository dremonkey/agents-and-skills (2 stars, last pushed 27d ago), licensed MIT. It adds 88 tokens to every session and 1,969 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…