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.
git 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/commands/lugassawan/swe-workbench/cleanup-merged)<a href="https://agentmods.dev/commands/lugassawan/swe-workbench/cleanup-merged"><img src="https://agentmods.dev/badge/commands/lugassawan/swe-workbench/cleanup-merged.svg" alt="Measured on agentmods" 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 | $0.00013 | $0.00284 |
| Opus 5 | $0.00006 | $0.00142 |
| Sonnet 5 | $0.00003 | $0.00057 |
| Haiku 4.5 | $0.00001 | $0.00028 |
Grade A, and why
cleanup-merged 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 7d 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.
What it actually says
Target: $ARGUMENTS (PR number if provided; otherwise derive from current branch)
Invoke swe-workbench:workflow-cleanup-merged to perform the full cleanup.
Pass the PR number from $ARGUMENTS to the skill if provided. If $ARGUMENTS is empty, the skill will derive the target branch from the current branch.
When the skill completes, print a summary listing each artifact (worktree, local branch, remote branch) and whether it was removed or was already gone, plus whether local main was synced to origin/main.
Output
The swe-workbench:workflow-cleanup-merged skill produces a structured artifact summary. Expect one status line per artifact:
- Worktree — path and whether it was removed or was already absent.
- Local branch — branch name and whether it was deleted or was already gone.
- Remote branch — remote ref and whether it was deleted, was already gone, or was skipped (no push permission).
- Main sync — whether local
mainwas fast-forwarded toorigin/mainor was already up to date.
Total lines: four. No severity tiers — this is a cleanup confirmation, not a findings report.
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.
- 7d ago First seen · 24 lines · 13 tokens per session scan A 8a4a6df15848
cleanup-merged is a command published in the GitHub repository lugassawan/swe-workbench (2 stars, last pushed 2d ago), licensed MIT. It adds 13 tokens to every session and 284 once invoked, about $0.0001 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 commands, from other repositories
pr
Create a pull request with zetetic-standard review and documentation.
commit
Create a git commit that meets the zetetic standard.
spawn
Spawn an agent as a standalone Claude Code session in an isolated git worktree.
review
Fast review of staged changes. Critical findings only — no style nits.
pre-commit
Run zetetic pre-commit checks manually on staged files.
pre-push
Run the full review skill on all changes since last push.