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-wake-angry-drunk-captain)<a href="https://agentmods.dev/commands/scienceisneato/slop-mop/sm-wake-angry-drunk-captain"><img src="https://agentmods.dev/badge/commands/scienceisneato/slop-mop/sm-wake-angry-drunk-captain/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-wake-angry-drunk-captain"><img src="https://agentmods.dev/badge/commands/scienceisneato/slop-mop/sm-wake-angry-drunk-captain.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 | $0.00572 |
| Opus 5 | $0.00000 | $0.00286 |
| Sonnet 5 | $0.00000 | $0.00114 |
| Haiku 4.5 | $0.00000 | $0.00057 |
Grade A, and why
sm-wake-angry-drunk-captain 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 11d 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
/sm-wake-angry-drunk-captain — escalate to the human
The last-resort verb. Use it ONLY when the loop is genuinely exhausted:
barnacles filed, gates green or truly unfixable, and the single remaining move
is a human judgment call no sm verb can make for you.
The standing order is "do not wake the captain unless there's an emergency." He is asleep. He is angry. He is drunk. He went below decks because the crew swore they had it handled. Picture his face before you reach for this.
sm wake-angry-drunk-captain \
--objective "what you were trying to get done" \
--verbs-tried "sm swab — green" \
--verbs-tried "sm scour — green" \
--verbs-tried "sm buff 42 — CI green, no unresolved threads" \
--why-stuck "no remaining verb advances; the blocker is a product/design call" \
--decision "the ONE call only a human can make" \
--option "approach A" \
--option "approach B"
All four of --objective, --verbs-tried, --why-stuck, and --decision are
required. Invoke the verb without them and it reads the standing order back to
you and refuses — that friction is the point. If you can't fill every line, you
don't have an emergency, you have unfinished work. Go back to sm sail.
A valid summons writes .slopmop/last_captain_summons.md and halts the loop
with a non-zero exit. It does not read your terminal — an agent's stdin is
a pipe, never a live human, so forcing a prompt would make this verb unreachable
in the exact stuck-in-a-loop case it exists for. Instead it speaks the same
JSON-envelope contract as every other verb:
data.relay_to_human— the captain's question, laid out for the human, ending on a direct ask. Show this to the user verbatim.data.agent_directive— the instruction back to you: your turn is over. Displayrelay_to_human, then stop and wait. Do not run another verb. Do not continue the loop.
The human answers in the chat; their reply is the captain's orders. Carry them out — and do not wake him again. You cannot satisfy this verb alone; that is the point.
Prerequisite: sm must be installed. If command not found, suggest:
pipx install slopmop[all]
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.
- 11d ago First seen · 48 lines · 0 tokens per session scan A b827933a4c04
sm-wake-angry-drunk-captain is a command published in the GitHub repository ScienceIsNeato/slop-mop (6 stars, last pushed 22d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 572 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
strip
This is the task-based stripper, not the always-on prior: a deliberate cleanup pass you asked for. Apply the fp-minify doctrine to the target and remove or compress comments that don't earn their place.
conjure-config
Set, view, or remove conjure preferences. Asks questions to understand what you want, then writes plain-language instructions that conjure commands follow automatically.
patrol-status
Show patrol dashboard — mode, tier, health, verification, config.
patrol-help
List all Patrol commands, skills, and config options.
patrol-keywords
Manage custom trigger keywords — list, add, remove, or reset.
patrol-config
Show or edit patrol configuration.