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/ThrownLemon/claude-code-pluginsWrote 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/thrownlemon/claude-code-plugins/control)<a href="https://agentmods.dev/commands/thrownlemon/claude-code-plugins/control"><img src="https://agentmods.dev/badge/commands/thrownlemon/claude-code-plugins/control/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/thrownlemon/claude-code-plugins/control"><img src="https://agentmods.dev/badge/commands/thrownlemon/claude-code-plugins/control.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 | $0.00015 | $0.00588 |
| Opus 5.5 | $0.00006 | $0.00235 |
| Sonnet 5.5 | $0.00003 | $0.00118 |
| Haiku 4.5 | $0.00002 | $0.00059 |
Grade C, and why
control scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
1. **Reject dangerous tokens.** If a value contains `$(`, backticks, `;`, `|`, `&`, `>`, `<`, or starts with `-` (could be mistaken for a flag), refuse and ask the user to rephrase. **Double-quoting does NOT block comman How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Input Safety — apply before any Bash invocation
Treat every $ARGUMENTS.* value as untrusted input. Before passing any value to the Bash tool:
- Reject dangerous tokens. If a value contains
$(, backticks,;,|,&,>,<, or starts with-(could be mistaken for a flag), refuse and ask the user to rephrase. Double-quoting does NOT block command substitution —"$(rm -rf /)"still executes inside double quotes. - Prefer the Bash tool's argv contract over constructed shell strings. When you must use a shell string, single-quote the value and escape embedded single quotes ('''), or build the command via
printf %q. - Any
"$ARGUMENTS.foo"patterns shown below are illustrative. Sanitize the value first; never blindly substitute.
Workflow
1. Sanitize and resolve action
Validate $ARGUMENTS.action (or default to status):
- Lowercase the value.
- It must be one of:
pause,resume,cancel,status. - Reject any value containing
$(, backticks,;,|,&,>,<, or starting with-. - If it is none of the accepted values, tell the user the valid options and stop.
2. Dispatch
status
bambu status --json
Parse the JSON and present a formatted status block (same format as /bambu:status).
pause
bambu gcode pause
Report success or failure.
resume
bambu gcode resume
Report success or failure.
cancel — ⚠️ DESTRUCTIVE
Cancelling aborts the current print. The partial print and filament are usually unrecoverable.
Before executing, show a confirmation prompt:
🔴 Cancel the current print? This will abort the running print. Filament and progress will be lost. Reply yes to proceed.
Wait for a clear affirmative response. If the user does not confirm, stop without running the command.
After confirmation:
bambu gcode cancel
Report the result.
3. Report result
For every action, show the CLI output or a clear success/failure message. Suggest /bambu:status to verify the new 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 · 76 lines · 15 tokens per session scan C f37af2ed3912
control is a command published in the GitHub repository ThrownLemon/claude-code-plugins (2 stars, last pushed 4mo ago), licensed MIT. It adds 15 tokens to every session and 588 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
tapeout
Produce a complete, fab-ready export bundle for a routed board — or refuse loudly. Superset of the manufacturing-readiness skill: runs the three sign-off pre-gates, then adds a BOM part-number-resolution gate, a per-rule warning-review gate (assembly-affecting warnings block unless explicitly acknowledged), schematic…
eol-report
EOL/EOS risk report — devices, OS versions, and firmware approaching or past end-of-life/end-of-support, prioritized by criticality.
cisco-catalyst-ta-setup
Configure and validate the Cisco Catalyst Add-on (TAciscocatalyst), including SD-WAN API/BFD, UTD and ZBFW syslog routing, Cyber Vision, ISE, Catalyst Center, and the beta IOS-XE CLI collector.
rvcsi-calibrate
Learn a v0 per-subcarrier baseline (mean amplitude) from a .rvcsi capture.
esp-harden
Harden and inspect ESP32 firmware for field failures, crashes, memory, and security.
pentest-wireless
You are an expert wireless security tester covering Wi-Fi, Bluetooth, and IoT radio protocols. For AUTHORIZED testing only.