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/doctor)<a href="https://agentmods.dev/commands/lugassawan/swe-workbench/doctor"><img src="https://agentmods.dev/badge/commands/lugassawan/swe-workbench/doctor/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/doctor"><img src="https://agentmods.dev/badge/commands/lugassawan/swe-workbench/doctor.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 | $0.00071 | $0.00374 |
| Opus 5.5 | $0.00028 | $0.00150 |
| Sonnet 5.5 | $0.00014 | $0.00075 |
| Haiku 4.5 | $0.00007 | $0.00037 |
Grade A, and why
doctor 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.
What it actually says
Run the preflight diagnostic and print the results verbatim:
command -v swe-workbench-doctor >/dev/null 2>&1 || {
echo "swe-workbench runtime commands not on PATH — reinstall or update the swe-workbench plugin." >&2
exit 1
}
swe-workbench-doctor
Print the full stdout output exactly as produced — do not summarise, truncate, or reformat it.
The script probes six runtime dependencies: gh, git, jq, rimba, claude, and python3. It also checks gh auth status and appends the result to the gh row. Each tool is marked ✓ (present) or ✗ (missing). When a tool is missing the row includes an install hint. The dependency summary line reports the count of missing dependencies or confirms all are present.
Inside a git repository, a separate Repo hygiene section follows: it checks whether .claude/cache/ (the plugin's workflow-state and skill-usage sidecar directory) is gitignored, and whether any file under it is already tracked. Each issue is reported as a warning with a remediation hint — the check never writes to .gitignore or runs git rm itself. Outside a git repository the section is omitted entirely. This section has its own warning count, independent of the dependency summary.
This command takes no arguments and makes no changes to state.
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 · 22 lines · 71 tokens per session scan A 1253f139ca8d
doctor is a command published in the GitHub repository lugassawan/swe-workbench (3 stars, last pushed yesterday), licensed MIT. It adds 71 tokens to every session and 374 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 2026-08-31.
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.