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.
npx agentmods add skills/pr3m/claude-code-bash-smart-approve/uninstallnpx skills add pr3m/claude-code-bash-smart-approve --skill uninstallgit clone --depth 1 https://github.com/pr3m/claude-code-bash-smart-approveWrote 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/skills/pr3m/claude-code-bash-smart-approve/uninstall)<a href="https://agentmods.dev/skills/pr3m/claude-code-bash-smart-approve/uninstall"><img src="https://agentmods.dev/badge/skills/pr3m/claude-code-bash-smart-approve/uninstall.svg" alt="Measured on agentmods" 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 | $0.00050 | $0.00444 |
| Opus 5 | $0.00025 | $0.00222 |
| Sonnet 5 | $0.00010 | $0.00089 |
| Haiku 4.5 | $0.00005 | $0.00044 |
Grade D, and why
bash-smart-approve:uninstall scanned grade D with 2 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 4d 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.
> "This will remove the PreToolUse hook from `~/.claude/settings.json` and (optionally) delete your config + log. Proceed?" Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- Do not delete the plugin directory itself. That's managed by `/plugin uninstall` (marketplace) or `rm -rf <clone-path>` (manual). What it actually says
Uninstall
Reverse what /bash-smart-approve:install did. Asks for confirmation at each step — nothing is silently deleted.
Step 1 — Confirm intent
"This will remove the PreToolUse hook from
~/.claude/settings.jsonand (optionally) delete your config + log. Proceed?"
If no → stop.
Step 2 — Unwire the hook
Read ~/.claude/settings.json. Find entries under hooks.PreToolUse[*].hooks[*] whose command references bash-smart-approve / approve.js and remove them. If a matcher block becomes empty, remove the whole block.
Show the diff. Apply on approval.
Also check project-level settings (.claude/settings.json, .claude/settings.local.json) and offer to unwire there too.
Step 3 — Offer to delete config
Ask: "Delete the bash-smart-approve config file(s) too? (you can keep them if you plan to reinstall)"
Candidates:
$CLAUDE_PLUGIN_DATA/config.json~/.claude/bash-smart-approve.json<cwd>/.claude/bash-smart-approve.json
Step 4 — Offer to delete log
Ask: "Delete the audit log at ~/.claude/bash-smart-approve.log?" Default: keep.
Step 5 — Do NOT
- Do not delete the plugin directory itself. That's managed by
/plugin uninstall(marketplace) orrm -rf <clone-path>(manual). - Do not touch
permissions.allowrules — those were already the user's, not our creation.
Step 6 — Summary
Confirm what was removed and remind user:
- Reinstall anytime via
/bash-smart-approve:install - Restart Claude Code (or
/hooks) for the hook removal to take effect
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.
- 4d ago First seen · 47 lines · 50 tokens per session scan D eef731e66dae
bash-smart-approve:uninstall is a skill published in the GitHub repository pr3m/claude-code-bash-smart-approve (1 stars, last pushed 4mo ago), licensed MIT. It adds 50 tokens to every session and 444 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it D with 2 findings (reads agent configuration directories, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
audit
Audit local Claude Code transcript usage and summarize likely token hotspots. Use when the user asks where Claude Code tokens are going or wants evidence before optimizing.
comms-context
Fetch on-call and discussion context from Slack threads and PagerDuty incidents — participants, timeline, and status. Auto-loads on Slack permalinks or PagerDuty incident references. Keywords — Slack, thread, PagerDuty, on-call.
explain-last-decision
Explain the most recent ask or deny decision emitted by caushell-claude.
bash-defensive-patterns
Master defensive Bash programming techniques for production-grade scripts. Use when writing robust shell scripts, CI/CD pipelines, or system utilities requiring fault tolerance and safety.
optimize
Diagnose and reduce Claude Code token usage for a project or session using context hygiene, model and effort routing, MCP minimization, output trimming/sanitizing, subagent discipline, and measurement. Use when the user asks to lower Claude Code token usage, cost, context bloat, or usage-limit burn.
setup
Interactive or guided project setup for Claude Code token optimizer settings. Use when the user asks to install, configure, setup, enable hooks, or choose token-saving options interactively.