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 agentmods add skills/fprochazka/claude-code-plugins/mr-statusnpx skills add fprochazka/claude-code-plugins --skill mr-statusgit clone --depth 1 https://github.com/fprochazka/claude-code-pluginsWhat 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 | $0.00114 | $0.02298 |
| Opus 5 | $0.00057 | $0.01149 |
| Sonnet 5 | $0.00023 | $0.00460 |
| Haiku 4.5 | $0.00011 | $0.00230 |
Grade A, and why
mr-status 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.
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mr-status
Determine the review-and-merge status of one merge request, or of a set of them. Is it rebased, is CI green, who reviewed it, what is still unresolved, and what blocks the merge right now. Every value is read at run time from the host API and from the MR threads.
Load the glab skill and the glab-discussion skill before the first call. The command recipes live in references/commands.md. Read that file before running anything. This skill covers GitLab, because it ships in the glab plugin. The GitHub equivalent lives in a gh plugin.
Prefer glab-discussion read --dump for all comment data. It writes one file per thread and it handles pagination. The raw discussions API is the fallback when that CLI is absent.
The mistake this skill exists to prevent
Read the latest summary verdict per reviewer, plus the count of currently unresolved threads. Never infer "this MR has problems" from the presence of historical finding notes. A reviewer can post major findings on Monday, see them fixed on Tuesday, and post a clean summary on Wednesday. The old notes stay in the thread list forever. Counting them as live problems produces a false "found issues" status. Exactly two signals are authoritative: the newest summary verdict per reviewer, and the number of threads whose header says Resolved: no.
Finding the newest verdict is not the same as finding the newest thread. A reviewer keeps its summary in one thread and either edits that note or appends to it, so the summary thread is usually one of the oldest on the MR while it holds the freshest verdict. Sorting threads by their timestamp and reading the newest one therefore returns a finding note, and reading a thread from the top returns round one of a summary rewritten many times since. Locate the reviewer's summary thread by kind, then read its last note. references/commands.md §5 has the recipe.
Inputs
Normalize every MR reference to <repo-path>!<iid>:
What ships with it
1 file 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.
- 2d ago First seen · 99 lines · 114 tokens per session scan A 35b6efa62ff9
mr-status is a skill published in the GitHub repository fprochazka/claude-code-plugins (11 stars, last pushed 5d ago), licensed MIT. It adds 114 tokens to every session and 2,298 once invoked, about $0.0006 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…