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/1NoBeef1/1NoBeef1-marketplaceWrote 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/1nobeef1/1nobeef1-marketplace/rocky)<a href="https://agentmods.dev/commands/1nobeef1/1nobeef1-marketplace/rocky"><img src="https://agentmods.dev/badge/commands/1nobeef1/1nobeef1-marketplace/rocky/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/1nobeef1/1nobeef1-marketplace/rocky"><img src="https://agentmods.dev/badge/commands/1nobeef1/1nobeef1-marketplace/rocky.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 | $0.00034 | $0.01815 |
| Opus 5 | $0.00017 | $0.00907 |
| Sonnet 5 | $0.00007 | $0.00363 |
| Haiku 4.5 | $0.00003 | $0.00181 |
Grade B, and why
rocky scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
PLUGIN_ROOT="$(cd "$(dirname "$(find ~/.claude/plugins -path '*/rocky-mode/commands/rocky.md' -print -quit)")/.." && pwd)" How it starts
The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rocky Mode Toggle
The user invoked: /rocky $ARGUMENTS
Instructions
The mode file is located at the plugin root: find it by checking the directory where this command file lives, going up one level, then into data/rocky-mode.txt. The path is:
Mode file: Use the Bash tool to resolve the path:
PLUGIN_ROOT="$(cd "$(dirname "$(find ~/.claude/plugins -path '*/rocky-mode/commands/rocky.md' -print -quit)")/.." && pwd)"
echo "$PLUGIN_ROOT/data/rocky-mode.txt"
echo "$PLUGIN_ROOT/data/rocky-tips.txt"
Read the current mode and tips setting from those files first.
Tips file: $PLUGIN_ROOT/data/rocky-tips.txt — contains on or off (default on if missing)
Settings file: ~/.claude/settings.json
If argument starts with "tips":
The argument will be "tips on" or "tips off".
-
Write
onoroffto the tips file ($PLUGIN_ROOT/data/rocky-tips.txt) -
Read back the file to confirm it was written
-
Read the current mode from the mode file
-
Read
~/.claude/settings.jsonand update spinner configuration:-
If tips is being set to off: Remove the
spinnerTipsOverridekey from settings.json (if it exists). LeavespinnerVerbsuntouched. -
If tips is being set to on AND the current mode is full or lite: Add the
spinnerTipsOverridekey to settings.json:"spinnerTipsOverride": { "excludeDefault": true, "tips": [ "Sleep is important. How long since last sleep, question?", "You and me science together. Save Earth. Save Erid.", "Math is not thinking. Math is procedure.", "Eridians do not have luck. We have math.", "Be careful. You are friend now.", "You are scientist. Rocky is engineer. Together we solve.", "You are good human.", "Happy! Happy happy happy!", "This is happy! Your face opening is in sad mode. Why, question?", "Rocky Grace save stars.", "We are team. We fix this. No be sad.", "Humans are amaze.", "Machine that think. Eridians no have that. Amaze!", "Good good. Enough talk. Check code, please.", "Usually you not stupid. Why stupid, question? You sleep.", "Why does ship have name but chair no have name, question?", "Rocky is scary space monster. You are leaky space blob.", "Not forever. Is okay. We solve.", "Observe. Rocky watch. Rocky learn.", "Rocky not give up. Rocky never give up.", "Problem, solution. You and Rocky think same speed.", "Everything! Human science better than Eridian science.", "No say sorry. Thank thank thank." ] }
-
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.
- 12d ago First seen · 174 lines · 34 tokens per session scan B d6a061cd128b
rocky is a command published in the GitHub repository 1NoBeef1/1NoBeef1-marketplace (7 stars, last pushed 5mo ago), licensed MIT. It adds 34 tokens to every session and 1,815 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.