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-hotfixgit 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-hotfix)<a href="https://agentmods.dev/skills/lugassawan/swe-workbench/workflow-hotfix"><img src="https://agentmods.dev/badge/skills/lugassawan/swe-workbench/workflow-hotfix/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-hotfix"><img src="https://agentmods.dev/badge/skills/lugassawan/swe-workbench/workflow-hotfix.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 | $0.00079 | $0.02381 |
| Opus 5.5 | $0.00032 | $0.00952 |
| Sonnet 5.5 | $0.00016 | $0.00476 |
| Haiku 4.5 | $0.00008 | $0.00238 |
Grade A, and why
workflow-hotfix 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 1mo 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow: Hotfix (branch-based, deferred verification)
Announce at start: "I'm using the workflow-hotfix skill to ship this as a fast branch-based hotfix."
When to invoke
/swe-workbench:hotfixcommand.- A P0/incident fix where the PR must go up before verify/review complete.
When NOT to invoke
- Non-urgent work →
/swe-workbench:implement(worktree-isolated, verify-before-PR). - Mid-PR follow-on →
/swe-workbench:extend. - Pure diagnosis with no urgency to ship →
/swe-workbench:debug.
Why the lifecycle is reordered
swe-workbench:workflow-development's Mode B hard-enforces verify → review → deliver so a broken change never
reaches a reviewer. A hotfix inverts the trade: the PR must exist now so reviewers, CI, and
stakeholders see it immediately; verification and review still happen, just after, against the
open PR. The deferred-verification marker on the PR body is what keeps that trade-off visible
instead of silently becoming permanent debt — swe-workbench:workflow-cleanup-merged reads it at merge time and
offers a backfill follow-up.
Phase 1 — Branch (forced, no worktree)
Never invoke the worktree provider (rimba add / superpowers:using-git-worktrees) — a hotfix
stays in the current checkout. If uncommitted changes are present (git status --porcelain),
stop and ask before switching branches.
DEFAULT_BRANCH=$(gh repo view --json defaultBranchRef -q .defaultBranchRef.name 2>/dev/null \
|| git symbolic-ref refs/remotes/origin/HEAD 2>/dev/null | sed 's@^refs/remotes/origin/@@' \
|| echo main)
git checkout "$DEFAULT_BRANCH" && git pull --ff-only origin "$DEFAULT_BRANCH"
git checkout -b "hotfix/<slug>"
Derive <slug> (kebab-case) from the ticket ref or a short symptom summary — same slugging as
rimba's own <task> normalization. --ff-only is non-negotiable (plain pull can synthesize a
merge commit on a stale local default branch).
Phase 2 — Implement (TDD relaxed)
Apply the minimal fix via superpowers:executing-plans or direct edits for a single-file change.
TDD is intentionally relaxed here — no test-first; the regression test is the deferred work
this command's marker tracks. Escalate a genuine design fork to swe-workbench:senior-engineer rather than
guessing (unchanged rule from swe-workbench:workflow-development).
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.
- 1mo ago First seen · 154 lines · 79 tokens per session scan A c835cbb297c0
workflow-hotfix is a skill published in the GitHub repository lugassawan/swe-workbench (3 stars, last pushed 4d ago), licensed MIT. It adds 79 tokens to every session and 2,381 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 2026-09-03.
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"…
pixiv-cli-ci
Diagnose pixiv-cli GitHub Actions failures and verify current-head quality, platform, PR-verification, native/browser, and release evidence. Use for CI readiness, failed or stalled runs, or an explicitly authorized rerun/cancel/dispatch; default to read-only evidence gathering.
resolving-merge-conflicts
Use when a git merge or rebase reports conflicts and the operation is in progress.
bug-fix
Investigate, reproduce, and safely fix a bug with regression protection. Composes context, diagnosis, architecture, code quality, and testing guardrails into a reproduce-first repair workflow. Use when the user says 'fix this bug', 'debug this', 'investigate this failure', 'patch this regression', 'repair this issue'…
refactor-safely
Restructure existing code safely without changing externally observable behavior. Composes context, design, architecture, code quality, and testing guardrails into a characterization-first refactoring workflow. Use when the user says 'refactor this', 'clean this up', 'untangle this module', 'move this to the right…
git-investigate
Git history investigation. Use when: tracking code changes, finding where bugs were introduced, root cause analysis. Not for: code exploration (use code-explore), issue analysis (use issue-analyze). Output: history trace + root cause report.