validate

validate is a command for Claude Code from xtofuub/frida-mcp-server. It costs 19 tokens per session (307 once invoked), scanned A, original, MIT.

A review gate for security findings from mobile app testing. It checks whether each finding can be reproduced, has real impact, is reachable by an attacker, and matches a MASVS security control.

In plain words
What is it for?
Use it to retest candidate issues with Frida, check evidence and scope, assign severity, map findings to MASVS, and record the validated results.
Why use it?
It removes weak, duplicate, theoretical, or unsupported findings before they are reported.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/xtofuub/frida-mcp-server/validate
Clone the repo
git clone --depth 1 https://github.com/xtofuub/frida-mcp-server

Made for: Claude Code.

Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 307 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00019 $0.00307
Opus 5 $0.00010 $0.00153
Sonnet 5 $0.00004 $0.00061
Haiku 4.5 $0.00002 $0.00031

Measured 3d ago against content hash aa8c4e3a1911, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

validate 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 3d 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.

.claude/commands/validate.md · 24 lines

What it actually says

Validate the candidate findings for $ARGUMENTS. Delegate to the ios-validator subagent. Every candidate must clear the 7-question gate:

  1. Reproducible? Re-run the exact mcp__frida__* calls — does it trigger again?
  2. Real impact? Concrete attacker capability, not theoretical.
  3. In scope / app's fault? Not OS behavior, not a deliberate debug build artifact.
  4. Attacker-reachable? Reachable without already owning the device/root, or state the precondition honestly.
  5. Not a duplicate? Check python scripts/memory.py query audit --bundle <id>.
  6. Evidence captured? Request/response, file contents, key material, or trace.
  7. MASVS-mapped? Tie to a control in references/masvs-checklist.md; assign severity (🔴/🟠/🟡/🟢).

Drop anything that fails. For survivors, write the validated record: python scripts/memory.py log audit --bundle <id> --json '{...}'.

Output: a kept/killed table with the reason for each kill, and the validated set ready for /report.

Changes

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.

  1. 3d ago First seen · 24 lines · 19 tokens per session scan A aa8c4e3a1911

Subscribe to this mod's changes

validate is a command published in the GitHub repository xtofuub/frida-mcp-server (3 stars, last pushed 2mo ago), licensed MIT. It adds 19 tokens to every session and 307 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.