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/smrafiz/claude-superchargerWrote 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/smrafiz/claude-supercharger/sc-autopilot)<a href="https://agentmods.dev/commands/smrafiz/claude-supercharger/sc-autopilot"><img src="https://agentmods.dev/badge/commands/smrafiz/claude-supercharger/sc-autopilot/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/smrafiz/claude-supercharger/sc-autopilot"><img src="https://agentmods.dev/badge/commands/smrafiz/claude-supercharger/sc-autopilot.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 | $0.00548 |
| Opus 5 | $0.00000 | $0.00274 |
| Sonnet 5 | $0.00000 | $0.00110 |
| Haiku 4.5 | $0.00000 | $0.00055 |
Grade C, and why
sc-autopilot scanned grade C 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 yesterday.
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.
While autopilot is on, Supercharger auto-approves **every** permission request so you're not prompted. It only removes the yes/no friction — the safety hooks still run, so dangerous commands (`rm -rf`, force-push, creden Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
While autopilot is on, Supercharger auto-approves **every** permission request so you're not prompted. It only removes the yes/no friction — the safety hooks still run, so dangerous commands (`rm -rf`, force-push, creden This is a copy
100% identical to autopilot — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Time-boxed auto-approve — stop the yes/no prompts for a while. Arguments: $ARGUMENTS ( [session|global] | off | status)
While autopilot is on, Supercharger auto-approves every permission request so you're not prompted. It only removes the yes/no friction — the safety hooks still run, so dangerous commands (rm -rf, force-push, credential leaks, curl|bash, self-modification) stay blocked. Your own permissions.deny and permissions.ask rules are also honoured — autopilot never auto-approves a call they cover. It auto-expires after the duration you give it, up to a ceiling of 8 hours (a full workday, so it can't be left on forever). Ask for more than the ceiling and it's clamped to the ceiling with a loud notice — never silently. Raise or lower the ceiling with SUPERCHARGER_AUTOPILOT_MAX_HOURS=<hours>.
Scope (default is per-session):
session(default) — only this Claude session auto-approves; other sessions are unaffected.global— every session on the machine auto-approves.
Run it (pass the argument straight through; default to status if none given):
bash ~/.claude/supercharger/tools/autopilot.sh $ARGUMENTS
Then report the tool's output verbatim.
/sc-autopilot 30m— auto-approve for 30 minutes in this session only. Accepts30m,2h,90s, or a bare number (minutes)./sc-autopilot 30m global— auto-approve for all sessions on the machine./sc-autopilot off— turn it off now (clears both this session's and the global window); normal prompts return./sc-autopilot status— show whether it's on (per-session and/or global) and how long is left.
Notes to surface to the user:
- This does not disable any safety guard — only the permission prompts.
rm -rf, force-push, credential leaks, etc. are still blocked by the PreToolUse hooks. - It ends automatically at the deadline (checked on each request — no background timer). The statusline shows a
⚡ Autopilot: Nm leftindicator while it's active. - Different from
/sc off, which disables all Supercharger guards (no safety floor). Autopilot keeps the safety floor.
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.
- yesterday Changed 984e87717330
- 11d ago First seen · 26 lines · 0 tokens per session scan C d78a70273cb2
sc-autopilot is a command published in the GitHub repository smrafiz/claude-supercharger (11 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 548 tokens. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). It is 100% identical to autopilot, differing in 2 lines, and is treated as a copy.
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.