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-readonly)<a href="https://agentmods.dev/commands/smrafiz/claude-supercharger/sc-readonly"><img src="https://agentmods.dev/badge/commands/smrafiz/claude-supercharger/sc-readonly/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-readonly"><img src="https://agentmods.dev/badge/commands/smrafiz/claude-supercharger/sc-readonly.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 | $0.00484 |
| Opus 5 | $0.00000 | $0.00242 |
| Sonnet 5 | $0.00000 | $0.00097 |
| Haiku 4.5 | $0.00000 | $0.00048 |
Grade C, and why
sc-readonly 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 10d 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.
- This is a **workflow guard** ("don't touch"), not a security sandbox — precise for the editor tools, best-effort for Bash. The always-on safety hooks (`rm -rf`, force-push, credential leaks) are the real floor and stay This is a copy
100% identical to readonly — 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
Read-only mode — "look, don't touch" for a while. Arguments: $ARGUMENTS ( [session|global] | off | status)
The inverse of /sc-autopilot: while read-only mode is on, Supercharger blocks every file edit (Write/Edit/MultiEdit/NotebookEdit) and every mutating shell command (rm, mv, git commit/push, npm install, sed -i, redirects that write a file, …). Reads, searches, and planning stay allowed. Great for exploring or reviewing a codebase without any risk of accidental changes. It auto-expires and is hard-capped at 2 hours.
Scope (default is per-session):
session(default) — only this Claude session is read-only.global— every session on the machine is read-only.
Run it (pass the argument straight through; default to status if none given):
bash ~/.claude/supercharger/tools/readonly.sh $ARGUMENTS
Then report the tool's output verbatim.
/sc-readonly 20m— read-only for 20 minutes in this session only. Accepts20m,2h,90s, or a bare number (minutes)./sc-readonly 20m global— read-only for all sessions on the machine./sc-readonly off— turn it off now; edits are allowed again./sc-readonly status— show whether it's on (per-session and/or global) and how long is left.
Notes to surface to the user:
- This is a workflow guard ("don't touch"), not a security sandbox — precise for the editor tools, best-effort for Bash. The always-on safety hooks (
rm -rf, force-push, credential leaks) are the real floor and stay active either way. - It ends automatically at the deadline (checked on each tool call — no background timer). The statusline shows a
⚡ Read-only: Nm leftindicator while it's active. - Interacts cleanly with autopilot: read-only wins — a blocked edit is blocked even if autopilot would have auto-approved it (tighten beats loosen).
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.
- 10d ago First seen · 26 lines · 0 tokens per session scan C fcc9b1f3fae2
sc-readonly is a command published in the GitHub repository smrafiz/claude-supercharger (11 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 484 tokens. A static security scan graded it C with 1 finding (recursive force delete). It is 100% identical to readonly, 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.