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 commands/xtofuub/frida-mcp-server/scopegit clone --depth 1 https://github.com/xtofuub/frida-mcp-serverWhat 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 | $0.00017 | $0.00271 |
| Opus 5 | $0.00009 | $0.00135 |
| Sonnet 5 | $0.00003 | $0.00054 |
| Haiku 4.5 | $0.00002 | $0.00027 |
Grade A, and why
scope 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 2d 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.
What it actually says
Scope gate for $ARGUMENTS. Do not test anything until this passes.
- Identify the target. If ambiguous or empty, run
mcp__frida__appsand list installed apps with bundle id + pid; ask the user to pick. Never default to a hardcoded app. - Authorization check. Confirm the user is authorized to assess this app (own app, client engagement, bug-bounty program in scope). If unclear, stop and ask. Refuse unauthorized targets.
- Attach.
mcp__frida__connect(bundle_id)— ormcp__frida__spawnfor a clean launch. Report device, pid, and confirm the session withmcp__frida__sessions. - Baseline.
mcp__frida__info+mcp__frida__entitlementsso later phases have ground truth (bundle id, version, sandbox HOME, entitlements).
Output: a one-line GO/NO-GO with the confirmed bundle id and device.
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.
- 2d ago First seen · 21 lines · 17 tokens per session scan A df9cde09fe0d
scope is a command published in the GitHub repository xtofuub/frida-mcp-server (3 stars, last pushed 2mo ago), licensed MIT. It adds 17 tokens to every session and 271 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
android
Command "android" from zhagqn/agentwork, covering /android [subcommand] [args] and 执行前必读.
compose-test
Run Compose UI tests with Espresso. Verify critical user flows.
troubleshoot
Diagnose and resolve iOS issues in code, builds, runtime, and system behavior.
app-store-audit
Run an enterprise pre submission compliance audit on an iOS or Android app against Apple App Store and Google Play rejection rules. Pass a project path or run from the project root.
build-verify
Run the full build / test / analyze / format verification pass for this Flutter app.
ios-privacy
Prepare privacy labels, permissions, policy links, and data-use truth for iOS release.