fp-check Stop hook with matcher "*" fires on every unrelated session, causing forced LLM turns

Summary

The fp-check plugin's Stop hook in plugins/fp-check/hooks/hooks.json is registered with "matcher": "*", so it runs on every Claude Code session stop — not just sessions that actually used fp-check. This produces a noisy and expensive feedback loop on unrelated sessions.

Reproduction

1. Install the fp-check@trailofbits plugin via the marketplace.
2. Start any Claude Code session that has nothing to do with false-positive verification (e.g. a docs edit, an install troubleshooting session, a refactor).
3. When the assistant tries to stop, the Stop hook fires and runs the 30-second LLM completeness checker prompt.
4. The checker (correctly) recognizes the conversation is not about fp-check and tries to return approve per the prompt's own fallback rule, but the hook still consumes a full agent turn and injects a large block of stop-feedback into the conversation context.
5. Repeat on every stop attempt — the hook fires again and again, burning context and tokens with no benefit.

Why this is wrong

• Stop hooks with matcher: "*" run unconditionally. The completeness check is only meaningful when fp-check was actually used in the session.
• The hook prompt itself acknowledges this with the fallback "If the conversation is not about fp-check verification at all, return 'approve'" — meaning the author knew unrelated sessions would hit it but relied on a self-describing prompt to no-op out. That doesn't prevent the LLM call, the context bloat, or the forced turn.
• The companion SubagentStop hook is correctly scoped (it only matters for fp-check subagents), but the top-level Stop hook is over-broad.

Suggested fixes (any of)

1. Scope the hook to fp-check sessions. Set an environment variable or session marker when the fp-check skill activates and key the matcher off that, instead of "*".
2. Move the completeness check out of Stop and into the skill's own on-completion logic (e.g. as a final required step in the SKILL.md instructions). The skill knows when it's running; the harness doesn't.
3. Delete the top-level Stop hook entirely. The SubagentStop hook already enforces structured-output completeness on the actual fp-check subagents (data-flow-analyzer, exploitability-verifier, poc-builder), which is where the verification rigor lives. The Stop hook is redundant on top of that and only adds noise on unrelated sessions.

Option 3 is the simplest and loses no real coverage.

Workaround for users hitting this

```bash claude plugin disable fp-check@trailofbits ```

Re-enable only when actively running false-positive verification.

Affected file

`plugins/fp-check/hooks/hooks.json`, lines 4–15 (the `Stop` block).

Environment

• Claude Code (current as of 2026-04-08)
• macOS, fp-check plugin v1.0.0 from the trailofbits marketplace