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/sync)<a href="https://agentmods.dev/commands/lugassawan/swe-workbench/sync"><img src="https://agentmods.dev/badge/commands/lugassawan/swe-workbench/sync/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/commands/lugassawan/swe-workbench/sync"><img src="https://agentmods.dev/badge/commands/lugassawan/swe-workbench/sync.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 | $0.00102 | $0.00671 |
| Opus 5.5 | $0.00041 | $0.00268 |
| Sonnet 5.5 | $0.00020 | $0.00134 |
| Haiku 4.5 | $0.00010 | $0.00067 |
Grade A, and why
sync 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 21d 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 — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Target: $ARGUMENTS
Strategy resolution
Parse $ARGUMENTS left to right for --rebase, --check-redundancy, and --check-alignment:
--rebasepresent: strip the flag from the target text and use rebase strategy.--rebaseabsent: use the merge strategy (default).--check-redundancypresent: strip the flag from the target text and resolveCHECK_REDUNDANCY=on.--check-redundancyabsent: resolveCHECK_REDUNDANCY=off(default) — plainsyncstays unchanged.--check-alignmentpresent: strip the flag from the target text and resolveCHECK_ALIGNMENT=on.--check-alignmentabsent: resolveCHECK_ALIGNMENT=off(default).
Invoke swe-workbench:workflow-branch-sync, passing the resolved strategy (merge or rebase), CHECK_REDUNDANCY=on|off, and CHECK_ALIGNMENT=on|off.
Output
The swe-workbench:workflow-branch-sync skill produces a per-file resolution summary followed by a push prompt:
- Sync result — clean (fast-forward/no-conflict) or resolved-with-conflicts, and the strategy used (merge/rebase). Prefixed by the fetch status line from the skill's remote-ref refresh (
origin/<default> updated <old>→<new>orunchanged). - Per-file resolution — one line per conflicting file: which side was kept (mine/main/manual) and the one-line rationale surfaced by the
swe-workbench:conflict-resolversubagent. - Redundancy assessment (only when
--check-redundancywas passed — opt-in) — any whole-file candidates the branch added that the default branch already grew independently elsewhere, auto-applied (whole-file, zero references) or escalated to you per candidate. - Alignment assessment (only when
--check-alignmentwas passed — opt-in) — evaluates branch changes against main's recent history to detect architectural drift or paradigm shifts, escalating to you if drift is detected. - Push prompt — the result is left local; the skill asks before pushing. Merge pushes with
git push; rebase pushes withgit push --force-with-lease— never a plain force push.
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.
- 21d ago Changed · +10 tokens per session 1b947ed9b238
- 27d ago Changed · +3 lines · +17 tokens per session 10be76b8ac1e
- 1mo ago First seen · 29 lines · 75 tokens per session scan A 05c4557a8fcb
sync is a command published in the GitHub repository lugassawan/swe-workbench (3 stars, last pushed yesterday), licensed MIT. It adds 102 tokens to every session and 671 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 2026-08-31.
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.
review
Fast review of staged changes. Critical findings only — no style nits.
spawn
Spawn an agent as a standalone Claude Code session in an isolated git worktree.
pre-commit
Run zetetic pre-commit checks manually on staged files.
pre-push
Run the full review skill on all changes since last push.