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 lugassawan/swe-workbench --skill workflow-pr-reviewgit clone --depth 1 https://github.com/lugassawan/swe-workbenchWrote 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/lugassawan/swe-workbench/workflow-pr-review)<a href="https://agentmods.dev/skills/lugassawan/swe-workbench/workflow-pr-review"><img src="https://agentmods.dev/badge/skills/lugassawan/swe-workbench/workflow-pr-review/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/lugassawan/swe-workbench/workflow-pr-review"><img src="https://agentmods.dev/badge/skills/lugassawan/swe-workbench/workflow-pr-review.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 | $0.00106 | $0.07415 |
| Opus 5.5 | $0.00042 | $0.02966 |
| Sonnet 5.5 | $0.00021 | $0.01483 |
| Haiku 4.5 | $0.00011 | $0.00741 |
Grade A, and why
workflow-pr-review 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 5d 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 — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow: PR Review (remote-PR orchestration shell)
Announce at start: "I'm using the workflow-pr-review skill to review PR #N." (first-pass mode) or "...to re-check PR #N." (followup mode).
Mode resolution
This skill runs in one of two modes, chosen by the caller: first-pass (a fresh review) or followup (a re-check after the owner has addressed feedback). commands/review.md sets MODE=auto for a bare /swe-workbench:review <N> invocation and MODE=followup for --check-followup <N>. MODE=auto self-resolves to first-pass or followup at the top of Step 1 — see below — before mode-table interpolation happens, so everything downstream only ever sees a concrete first-pass/followup value.
Four values are derived from $MODE once, up front, and interpolated into every downstream bash block below — evaluated, not applied by hand:
| Var | first-pass |
followup |
|---|---|---|
MODE_TAG |
pr-review |
pr-followup |
STATE_SUFFIX |
(empty) | -followup |
CALLER_TAG |
general |
followup |
BYLINE |
_Reviewed by \reviewer`_` |
_Re-reviewed by \reviewer`_` |
The resolution itself happens at the top of Step 1 (the case "$MODE" block), which also echoes Mode: $MODE so mode selection is visible in the transcript — mirroring what commands/review.md already prints (Mode: <normalized-mode> (explicit) / Inferred mode: <mode> — reason: ...) for its own --mode selection.
When to invoke
- The user passes a PR number to
/swe-workbench:review(e.g./swe-workbench:review 123) — first-pass mode. - The user accepts the auto-detect prompt on
/swe-workbench:reviewno-arg ("Detected PR #N — review it? Replyyes") — first-pass mode. - The user runs
/swe-workbench:review --check-followup <N>— followup mode. - An agent or command needs to "review this remote PR end-to-end" — fetch + analyse + post + submit.
- Phrases (first-pass): "review PR 123", "do a peer review of #456", "fetch this PR and post deduped comments".
- Phrases (followup): "re-check PR 123", "check if my review comments were addressed", "follow up on review #456".
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.
- 5d ago Changed · +4 lines f30ada350a8d
- 10d ago Changed 91b21066f605
- 1mo ago Changed · +8 lines 48e2f879c1db
- 1mo ago Changed · +70 lines 96a0a20558f4
- 1mo ago First seen · 219 lines · 106 tokens per session scan A 116f6b9ac0ec
workflow-pr-review is a skill published in the GitHub repository lugassawan/swe-workbench (3 stars, last pushed 4d ago), licensed MIT. It adds 106 tokens to every session and 7,415 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
release
Cut a brooks-lint release: set the version in package.json, propagate it across all four plugin manifests and every version-bearing text file (README badges, docs site metadata), write the CHANGELOG entry, validate, then commit, push, tag, and publish the GitHub release. Triggers when the maintainer asks to "release"…
pr
Comprehensive PR/issue review - analyzes architecture, tests, identifies unrelated changes mixed in, drafts review comment or issue comment. Use when user asks to review a PR, check a PR, look at PR changes, or comment on an issue.
pr-threads-address
Address PR review feedback by systematically working through every unresolved PR review thread on the current branch's PR - analyze each comment, make the requested code changes (with tests where useful), commit, and optionally reply and resolve.
brooks-test
Test quality review drawing on twelve classic engineering books — with primary focus on xUnit Test Patterns, The Art of Unit Testing, How Google Tests Software, and Working Effectively with Legacy Code — that diagnoses structural problems in an existing test suite: brittleness, mock abuse, coverage illusions, slow…
deploy-landed
A deployment verification procedure that checks whether the intended code revision is actually running, its environment settings are present, and the product works. A deployment is the process of putting new software on a server or hosting platform.
procoder
Work like a senior developer in a repository governed by procoder: run the commit gate before calling anything done, format and lint through the binary, and drive the spec, plan, todo, backlog, and sprint chain in .procoder/. Use this skill when the repository contains a .procoder/ directory or an AGENTS.md naming…