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 JeonJe/claude-plugins --skill ma-open-mrgit clone --depth 1 https://github.com/JeonJe/claude-pluginsWrote 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/jeonje/claude-plugins/ma-open-mr)<a href="https://agentmods.dev/skills/jeonje/claude-plugins/ma-open-mr"><img src="https://agentmods.dev/badge/skills/jeonje/claude-plugins/ma-open-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/jeonje/claude-plugins/ma-open-mr"><img src="https://agentmods.dev/badge/skills/jeonje/claude-plugins/ma-open-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 | $0.01858 |
| Opus 5 | $0.00037 | $0.00929 |
| Sonnet 5 | $0.00015 | $0.00372 |
| Haiku 4.5 | $0.00007 | $0.00186 |
Grade A, and why
ma-open-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 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MA open PR/MR
Create or bind every approved project's PR/MR, then persist evidence that Phase 6 can recheck. Never treat a URL or human-formatted CLI output as proof — use provider JSON (gh ... --json, glab ... -F json / API) for every metadata claim. Deterministic contract scripts are not included in v1; perform each stated validation yourself before proceeding.
Invocation
/ma-open-mr ISSUE-KEY [--project PROJECT] [--draft] [--auto]
Without --project, process all projects in canonical approval. A partial run may save valid project evidence, but Phase 6 stays incomplete until the approved and recorded project sets match exactly.
References index
| File | When to read |
|---|---|
| references/diagrams.md | Step 2 — only when a diagram materially helps the body |
| references/gitlab-uploads.md | Step 2 — GitLab UI uploads, only with real UI evidence |
Canonical inputs
Read {stateRoot}/ISSUE-KEY/state.json and the workspace config.
- Require
gates.implementationApproval.status == "approved"and use onlygates.implementationApproval.projects[project].{base,target}. - Require the exact same project set in
state.worktrees; each entry suppliespath,base, andtarget. - Require workspace
platformto begithuborgitlab, the path to be a real Git worktree root ontarget, andoriginto match the eventual PR/MR URL. - Expand only a leading
~/. Reject shell syntax, control characters, missing paths, branch drift, extra projects, and duplicate paths. Never useeval.
Ownership policy
Resolve policy from approval.projects[project].mrPolicy, then the workspace config project mrPolicy, then the top-level mrPolicy. Approval has precedence.
{"mrPolicy":{"assignee":"alice","reviewers":["bob"],"reviewRequired":true}}
- Assignee may default to the authenticated author (
gh api user/glab api user). - Review is required by default. Resolve reviewers from explicit state/config; when none is configured, the reviewer defaults to the MR author (single-operator self-review model). Each reviewer must be a stable username; self-review by the author is permitted.
- Only an explicitly approved
reviewRequired:falsepermits no reviewer. - In
--auto, halt when a reviewer is rejected by the provider or absent from the MR after creation. Never fabricate a reviewer other than the author default. - Re-query the provider right after creation to confirm assignee/reviewers are non-empty — the omission is silent otherwise.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 143 lines · 75 tokens per session scan A edc75913f22a
ma-open-mr is a skill published in the GitHub repository JeonJe/claude-plugins (3 stars, last pushed 1mo ago), licensed MIT. It adds 75 tokens to every session and 1,858 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
git-advanced
Use when performing complex git operations -- rebasing, cherry-picking, resolving merge conflicts, bisecting bugs, managing stashes, cleaning history, or working with monorepos. Goes beyond basic commit/push/pull.
repo-polish
Use when setting up new repositories, auditing existing ones, or preparing repos for public visibility. Generates .gitignore, .env.example, README, and LICENSE files. Detects committed secrets and flags security issues.
oss-contrib
Use when contributing to open source projects from forked repositories. Handles upstream sync, CONTRIBUTING.md compliance, code style matching, PR preparation, and project-specific patterns. Activates for fork management, PR template filling, and upstream workflow compliance.
renovate-triage
Use when triaging open Renovate PRs across your own repos into merge / close / defer. Activates on "renovate triage", "review dep PRs", "monthly deps", or on the 1st of a month if deps are grouped monthly.
review-pr
Review a Pull Request in one of two postures: an expository "tour guide" that walks through changes in logical order, or an adversarial audit that assumes the change is wrong until proven safe and hunts for the failure mode. Triggers: "review PR #123", "adversarial review", "walk me through this PR", "PR tour guide"…
release
This skill should be used when the user wants to create a new release — bump version, tag, push, create GitHub release, and optionally publish to npm. Use when user says "release", "bump version", "publish", "cut a release", or "release candidate".