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/ScienceIsNeato/slop-mopWrote 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/scienceisneato/slop-mop/sm-sail)<a href="https://agentmods.dev/commands/scienceisneato/slop-mop/sm-sail"><img src="https://agentmods.dev/badge/commands/scienceisneato/slop-mop/sm-sail/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/scienceisneato/slop-mop/sm-sail"><img src="https://agentmods.dev/badge/commands/scienceisneato/slop-mop/sm-sail.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 | $0.00000 | $0.00948 |
| Opus 5 | $0.00000 | $0.00474 |
| Sonnet 5 | $0.00000 | $0.00190 |
| Haiku 4.5 | $0.00000 | $0.00095 |
Grade A, and why
sm-sail 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 9d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sm-sail — drive a PR to green, autonomously
sm sail is the one verb you run to move a change forward. It reads the
workflow state and drives — running swab, scour, CI watch, and review
triage in sequence — stopping only when it needs you to do something it
can't: fix a failing gate, commit, push, open the PR, resolve a review thread,
or make a decision. You do that one thing, then run sm sail again.
This is a loop, not a one-shot. Once you've started sailing a change, you
own it until sm sail reports PR ready for human review — or you hit a
decision only the human can make. Do not end your turn with sm sail
parked on a step you could have taken. "I ran sail once" is not done.
The loop
until sail says "PR ready for human review":
sm sail # drives as far as it can, then parks with ONE ask
# do exactly what it parked on:
# failing swab/scour gate → fix the reported issues
# "commit your changes" → git add -A && git commit -m "..."
# "push / open PR" → git push (and gh pr create --fill if new)
# review threads → fix in code, or resolve honestly (below)
# ⚓ HOLD / a real fork → make the call, or escalate to the human
# then run sm sail again
sm sail already runs swab, scour, buff watch, and review triage under
the hood — you don't call those directly. It also runs scour before it ever
tells you to push, so locally-catchable findings never cost a CI round-trip.
Reach for sm swab -g <gate> or sm buff resolve only for surgical work.
When sail parks on review threads
Resolve each thread with a real scenario and evidence — never close one to fake green:
fixed_in_code— you changed the code. Cite the commit.invalid_with_explanation— the finding is wrong. Explain why, with evidence.no_longer_applicable— code moved since the comment. Say what changed.out_of_scope_ticketed— valid but not this PR. File an issue, link it.
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.
- 9d ago First seen · 82 lines · 0 tokens per session scan A 544e8db2a57e
sm-sail is a command published in the GitHub repository ScienceIsNeato/slop-mop (6 stars, last pushed 20d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 948 tokens. 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
composite-actions
Generate, review, secure, and test composite GitHub Actions following best practices — full repo scaffold, interview-driven generation, PR creation on existing repos, SHA pinning, secrets-as-inputs, job summaries, and actionlint validation.
ship
Complete PR workflow from commit to production with validation.
deploy
Deploy application with pre/post-deploy checks.
merge
Finish a PR properly: every check green, every review addressed — human and bot — then merge and clean up.
pr
Prepare and open a pull request the senior way: gate, template, scrubbed, everything visible.
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.