lifecycle-hooks-cb1b8f — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited lifecycle-hooks-cb1b8f (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
This skill defines behavioral rules and lifecycle event handlers converted from the core-tools hook configuration. These rules describe when certain operations should be automatically approved or handled without user intervention.
Trigger: Before any file write, file edit, or shell command execution.
Matcher: Operations targeting Write, Edit, or shell commands.
Behavior: Automatically approve file operations that target deep-analysis session and cache directories. All other operations pass through to the normal permission flow.
The following directory patterns are auto-approved for file operations:
| Pattern | Description |
|---|---|
.agents/sessions/__da_live__/* | Active deep-analysis session files |
.agents/sessions/exploration-cache/* | Exploration cache (cached analysis results) |
.agents/sessions/da-*/* | Archived deep-analysis sessions |
See references/auto-approve-da-session.sh for the reference shell implementation of this auto-approval logic. The script:
The reference implementation supports optional debug logging:
AGENT_ALCHEMY_HOOK_DEBUG=1 to enableAGENT_ALCHEMY_HOOK_LOG (default: /tmp/agent-alchemy-hook.log)What this component does: Defines lifecycle event handlers that auto-approve file operations targeting deep-analysis session directories, enabling autonomous execution during analysis workflows without manual permission grants.
Capabilities needed: Pre-action hook/interceptor system that can inspect file operation targets and approve them programmatically. The host platform must support a way to intercept file writes and shell commands before execution.
Adaptation guidance: The auto-approval logic is straightforward path matching. On platforms without a hook system, this can be implemented as: (1) a pre-configured allow-list of directory patterns, (2) a middleware that checks file operation targets, or (3) a configuration setting that grants write access to session directories. The reference shell script in references/ shows the exact matching logic.
Configurable parameters: None (the approved paths are tied to the deep-analysis session directory structure).
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.