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 siarhei-belavus/agent-public --skill gitlab-mrgit clone --depth 1 https://github.com/siarhei-belavus/agent-publicWrote 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/siarhei-belavus/agent-public/gitlab-mr)<a href="https://agentmods.dev/skills/siarhei-belavus/agent-public/gitlab-mr"><img src="https://agentmods.dev/badge/skills/siarhei-belavus/agent-public/gitlab-mr/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/siarhei-belavus/agent-public/gitlab-mr"><img src="https://agentmods.dev/badge/skills/siarhei-belavus/agent-public/gitlab-mr.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 | $0.00075 | $0.01035 |
| Opus 5.5 | $0.00030 | $0.00414 |
| Sonnet 5.5 | $0.00015 | $0.00207 |
| Haiku 4.5 | $0.00007 | $0.00103 |
Grade A, and why
gitlab-mr 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 2mo 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitLab MR
Prefer a clean, reviewable MR over convenience. Never pull unrelated local changes into the branch just to make the working tree look tidy.
Workflow
-
Inspect repo state first.
- Run
git status --short. - Run
git branch --show-current. - Run
git remote show origin | sed -n '/HEAD branch/s/.*: //p'to confirm the target branch. - Run
glab auth statusbefore attempting MR creation. - Identify unrelated modified or untracked files and keep them out of the MR.
- Read applicable repo instructions such as
AGENTS.mdbefore choosing validation commands.
- Run
-
Stage only the intended changes.
- Use explicit
git add <path...>. - Never use
git add -Aorgit add .in this repo for MR prep. - Re-check the staged set with
git diff --cached --stat. - Leave unrelated files, including user edits and stray backups, unstaged unless the user explicitly asked to include them.
- Use explicit
-
Create the branch before committing.
- Use the repo convention
codex/<topic>. - Base it on the current target branch, which is usually the
origin HEADbranch unless the user requested another base. - If already on a suitable feature branch created for the requested work, reuse it instead of branching again.
- Use the repo convention
-
Run the required validation for the touched scope.
- Read the repo instructions and run the mandated validation for the touched scope.
- If the repo does not specify validation, prefer the smallest command set that proves the change:
- targeted tests first
- then typecheck
- then lint
- If a command fails because of a real code issue, fix it before creating the MR.
- If a command fails because of an environment or dependency issue unrelated to the change, capture the exact failure in the MR description and final handoff.
-
Commit cleanly.
- Use one focused commit unless the user asked for a different history shape.
- Use a short imperative message.
- Do not amend or rebase unless the user explicitly asked.
- If commit hooks modify files, review the resulting diff before pushing.
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.
- 2mo ago First seen · 93 lines · 75 tokens per session scan A 25cb55f3034f
gitlab-mr is a skill published in the GitHub repository siarhei-belavus/agent-public (2 stars, last pushed 5mo ago), licensed MIT. It adds 75 tokens to every session and 1,035 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
pr
Draft a PR body from OMC's paper trail — the smallest visual that proves the change, evidence consumed from the verify protocol (never re-collected), reversibility from the ADR test on the diff, glossary language throughout.
merge-batch
Prepare and merge an owner-selected PR batch with contributor credit and exact-candidate admission. Use for a pasted PR list; combined focused validation is diagnostic, and every actual landing still requires its applicable checks and authorization.
otto-pr-review-loop
Run Polly and OCR on a PR until all findings settle.
engram-branch-pr
PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.
github-contributor
A step-by-step guide for contributing code, tests, documentation, or build changes to open-source projects you do not maintain. It explains how to prepare a pull request that follows the project’s rules and is easier for maintainers to review.
revdiff
Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in agterm/tmux/zellij/herdr/kitty/wezterm/cmux/ghostty/iterm2/emacs-vterm, captures annotations, and addresses them. Works in git, hg, and jj repos…