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 review-mrgit 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/review-mr)<a href="https://agentmods.dev/skills/dremonkey/agents-and-skills/review-mr"><img src="https://agentmods.dev/badge/skills/dremonkey/agents-and-skills/review-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/dremonkey/agents-and-skills/review-mr"><img src="https://agentmods.dev/badge/skills/dremonkey/agents-and-skills/review-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 | $0.00137 | $0.03359 |
| Opus 5 | $0.00068 | $0.01680 |
| Sonnet 5 | $0.00027 | $0.00672 |
| Haiku 4.5 | $0.00014 | $0.00336 |
Grade A, and why
review-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 11d 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 — 286 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Change Review — GitLab MR / GitHub PR
One skill, two providers, three modes. The platform-neutral pipeline (preflight → mode analysis → verification → briefing → forks → sanity gate → publish) lives here. Two layers plug into it:
- Provider — how to talk to the host. All
glab/ghmechanics live inprovider-gitlab.md/provider-github.md. This file never names a CLI; it calls operations by name (e.g.view-change,post-line-comment), and the provider file you load in Step 1a defines those operations. - Mode — what to analyze. Mode-specific analysis lives in one of three mode files. Step 1c/1d selects one.
Throughout this skill and its mode files, "the change" (and the shorthand
"MR/PR") means the GitLab MR or GitHub PR under review. Operation names
appear in code font and always resolve to a section in the loaded provider
file.
| Mode | When | Mode file |
|---|---|---|
| PLAN | Diff is predominantly planning prose: EPIC.md, PRDs, VISION docs, architecture docs, task files |
mode-plan.md |
| IMPL-FIRST | Diff is predominantly source/tests/config and the user has no prior review notes on the change | mode-impl-first.md |
| FOLLOWUP | Diff is source/tests/config and the user has already posted review comments in a prior pass | mode-followup.md |
When NOT to use — bail early
- Trivial diffs (one-line fix, typo, version bump, lockfile churn) — just eyeball and tell the user. Don't run the full discipline on something with no decisions in it.
- Neither GitLab nor GitHub. This skill only knows
glabandgh. For any other host, stop and tell the user.
Provider operations (the shared contract)
Both provider files implement this same catalog. Read the loaded provider file for the exact commands; reference operations by name everywhere else.
| Operation | Purpose |
|---|---|
view-change |
Fetch metadata (title, branch, description, commits) and capture the identifiers + anchoring SHAs every later operation needs |
list-files |
List changed files for the plan-vs-code classification |
my-prior-notes |
The current user's own prior review comments (IMPL-FIRST vs FOLLOWUP triage) |
raw-file |
A file's full contents at a SHA |
post-top-level |
The framing/narrative comment |
post-line-comment |
A comment pinned to a specific diff line (+ verify it attached) |
list-prior-threads |
All prior review threads by the current user, with positions + resolution state |
prior-review-head |
The head SHA at the time of the last review (delta boundary) |
delta-files |
Files changed between two SHAs |
reply-thread |
Append a note to an existing thread |
resolve-thread |
Mark a thread resolved |
delete-note |
Remove a mis-posted comment (recovery) |
What ships with it
5 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.
- 11d ago First seen · 286 lines · 137 tokens per session scan A 8eb73248de48
review-mr is a skill published in the GitHub repository dremonkey/agents-and-skills (2 stars, last pushed 27d ago), licensed MIT. It adds 137 tokens to every session and 3,359 once invoked, about $0.0007 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
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
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.
verify-behavior
Verify or reproduce visible product behavior by driving the real UI with pi-computer-use's checked tools, requiring verified expect postconditions and durable state evidence for meaningful UI flows. Use when triage needs visual reproduction, implementation needs behavioral proof, review needs interactive confirmation…
github-contributor
End-to-end playbook for shipping high-quality pull requests to open-source projects you don't maintain — discovery, CONTRIBUTING compliance, PR-size check, minimal-diff implementation, PR description with AI-assisted disclosure, conflict resolution, and post-submission maintainer interaction. Use whenever creating…
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…
oss-maintainer
Run an open-source project's issue/PR/release loop like a careful human maintainer — triage to root cause, absorb community PRs before duplicating them, gate every merge, ship honest releases, and thank the people doing your QA for free.