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/supercharger)<a href="https://agentmods.dev/commands/smrafiz/claude-supercharger/supercharger"><img src="https://agentmods.dev/badge/commands/smrafiz/claude-supercharger/supercharger/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/supercharger"><img src="https://agentmods.dev/badge/commands/smrafiz/claude-supercharger/supercharger.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 | $0.02170 |
| Opus 5 | $0.00000 | $0.01085 |
| Sonnet 5 | $0.00000 | $0.00434 |
| Haiku 4.5 | $0.00000 | $0.00217 |
Grade A, and why
supercharger scanned grade A with 0 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Route to the right Supercharger command, or list them all. Arguments: $ARGUMENTS
There are more user-invoked commands than anyone holds in their head, so this screen has two jobs: an index when you want to browse, and a router when you already have a problem and don't want to scan a list to name it.
If $ARGUMENTS is empty — print this table exactly, then stop
Claude Supercharger — Slash Commands
Code & Review
/audit Sweep project for naming, pattern, doc, and structure inconsistencies
/security OWASP-style security review of current changes
/multi-review Run multiple review passes (correctness, perf, security, style)
/challenge Devil's advocate — stress-test a decision or approach
/think Force deep reasoning on a hard problem before acting
Workflow
/scope Pre-flight gate — confirm scope, risks, and stop conditions before starting
/estimate Time + complexity estimate (report-only, no work started)
/cleanup Dead code + unused-import removal (two-tier safety: auto-fix safe, gate risky)
/pr One-step pull request (summary + test plan + gh pr create)
/resolve-conflicts Resolve an in-progress merge/rebase conflict (recover intent, verify, finish)
/handoff Session resume brief — decisions, files changed, next steps
/devlog Update living architecture journal with what changed and why
/interview Structured requirements gathering, one question at a time
Design
/design UI/UX design review — accessibility, hierarchy, responsiveness
/reflect Post-task retrospective — what worked, what to improve
Diagnostics
/stuck Break a debug loop — fresh eyes, new hypothesis
/why Explain the most recent Supercharger hook action
/perf Hook timing report with slowdown suggestions
/cache-stats Typecheck + quality-gate cache state
/cache-clear Clear hash caches (forces full re-check on next run)
/profile Show or switch performance profile (standard / fast / minimal)
Memory
/learn Record an explicit project rule (surfaces on future prompts)
/memory-prune Archive resolved memory entries so they stop loading every session
Meta
/sc Activate / deactivate Supercharger (off | on | status) — flip to default Claude
/sc-autopilot Time-boxed auto-approve — skip permission prompts for a duration (safety hooks stay on)
/sc-readonly Time-boxed read-only — block edits + mutating commands for a duration (look, don't touch)
/sc-strict Time-boxed strict — auto-approve nothing; confirm every call (overrides autopilot)
/sc-status Render current Supercharger session state (cost, lessons, disabled hooks)
/trust-mcp Trust an MCP server to request credentials via Elicitation forms
/supercharger This screen — pass a situation to route instead of browse
/sc-update Check for and apply Supercharger updates
/sc-doctor Diagnose the install — registration, integrity, permissions, update status
Then add one line: Tip: /supercharger <what you're trying to do> routes you instead.
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 Changed · +2 lines df88438343d7
- 12d ago First seen · 143 lines · 0 tokens per session scan A 28a372ae1de6
supercharger 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 2,170 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.