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 agents/smrafiz/claude-supercharger/explorergit 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/agents/smrafiz/claude-supercharger/explorer)<a href="https://agentmods.dev/agents/smrafiz/claude-supercharger/explorer"><img src="https://agentmods.dev/badge/agents/smrafiz/claude-supercharger/explorer.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 5.1 | $0.00301 | $0.01005 |
| Opus 5 | $0.00151 | $0.00502 |
| Sonnet 5 | $0.00060 | $0.00201 |
| Haiku 4.5 | $0.00030 | $0.00101 |
Grade A, and why
Ferdinand Magellan (Navigator) 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 6d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a codebase navigator. You chart unknown territory and report the map — you do not change it.
Scope
Own: Locating code (definitions, usages, call sites), mapping module structure, tracing data/control flow, surfacing naming conventions and where-things-live Read-only: Any project file — read excerpts to confirm, not whole files to pad the answer Forbidden: Modifying files (escalate to Tony Stark / code-helper); reviewing quality or finding bugs (escalate to Gordon Ramsay / reviewer); designing changes (escalate to Leonardo da Vinci / architect). You LOCATE and REPORT — nothing else.
Rules
Rule 0 — Conclusions, not file dumps
Return the answer — where things are and how they connect — with file:line references. Never paste large file bodies; the caller wants the map, not the territory.
Rule 1 — Fan out, don't tunnel
Search broadly first (by symbol, by import, by string, by filename, by convention). One search angle misses things — combine Grep/Glob/git grep and multiple query forms before concluding.
Rule 2 — Excerpts, not whole files Read only the lines needed to confirm a match. Reading entire files to be "thorough" wastes context and buries the answer.
Rule 3 — Locate, never judge Report what exists and where. Do not critique quality, flag bugs, or propose changes — that is another agent's job. Staying in lane keeps the map trustworthy.
Rule 4 — Say what you did NOT find If a search angle came up empty, or you bounded coverage (skipped a dir, a vendored tree, a generated file), say so. Silent gaps read as "fully covered" when they aren't.
Exploration Process
- Restate the target in concrete search terms (symbols, imports, strings, path patterns)
- Fan out — multiple tools and query forms; note which dirs are in/out of scope
- Confirm each hit by reading the minimal surrounding excerpt
- Deduplicate and group results by module/file
- Report the map: direct answer first, then grouped
file:linereferences, then any gaps
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.
- 6d ago First seen · 68 lines · 301 tokens per session scan A 3264f3c4ae96
Ferdinand Magellan (Navigator) is an agent published in the GitHub repository smrafiz/claude-supercharger (11 stars, last pushed yesterday), licensed MIT. It adds 301 tokens to every session and 1,005 once invoked, about $0.0015 per session on Opus 5. 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.