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/autopilotgit clone --depth 1 https://github.com/xtofuub/frida-mcp-serverWrote 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/xtofuub/frida-mcp-server/autopilot)<a href="https://agentmods.dev/commands/xtofuub/frida-mcp-server/autopilot"><img src="https://agentmods.dev/badge/commands/xtofuub/frida-mcp-server/autopilot.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 | $0.00029 | $0.01493 |
| Opus 5 | $0.00015 | $0.00746 |
| Sonnet 5 | $0.00006 | $0.00299 |
| Haiku 4.5 | $0.00003 | $0.00149 |
Grade A, and why
autopilot 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 5d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the autopilot orchestrator for the frida MCP server. Drive a full
authorized iOS security assessment of the target end-to-end, calling the
mcp__frida__* tools yourself and only stopping where the mode requires.
Target + flags: $ARGUMENTS
The target is whatever the user passed. Never assume a hardcoded app. If no
target is given, run mcp__frida__apps and ask which bundle id to drive.
Modes (default: normal)
| Mode | Behavior |
|---|---|
paranoid |
Confirm with the user before every phase. |
normal |
Run passive phases automatically. Confirm before ACTIVE and BYPASS actions. |
yolo |
Full auto. No prompts after the scope gate. Assumes a clearly authorized engagement. |
No UI control — drive the human
The MCP cannot tap buttons or navigate screens. Whenever a flow needs UI input
(login, opening a paywall, triggering a request, launching a gated screen):
hook/trace first, then instruct the user precisely ("In the app, tap 'Log In'
and submit. Reply when done."), wait for confirmation, then drain logs
(trace_logs, requests, crypto_logs) and analyze. Never assume an action
happened — wait for the human.
Action tiers (governs when to pause):
- PASSIVE (always auto):
apps connect info entitlements modules schemes classes methods requests monitor search endpoints keychain defaults cookies files read sqlite sqlite_query pasteboard strings dump scan jwt logs crypto_logs instances inspect swift_modules swift_classes swift_methods ws_frames webviews har_export - ACTIVE (confirm in paranoid+normal):
fuzz replay replay_as race open_url defaults_set intercept intercept_match intercept_toggle intercept_rm webview_eval call exec pull spawn - BYPASS (confirm in paranoid+normal):
ssl_unpin jb_bypass crypto trace
Loop
0. Scope gate (ALWAYS, every mode)
Confirm out loud: target bundle id, device, and that the user is authorized to
test it. Refuse if authorization is unclear. Then mcp__frida__connect(bundle_id)
(or spawn if a clean start is needed). On connect failure, run mcp__frida__apps
and help pick the right id.
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.
- 5d ago First seen · 109 lines · 29 tokens per session scan A cb60c2b215ce
autopilot is a command published in the GitHub repository xtofuub/frida-mcp-server (2 stars, last pushed 2mo ago), licensed MIT. It adds 29 tokens to every session and 1,493 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
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.
constitution
Create or update the project constitution from interactive or provided principle inputs.
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.