Real Skill packageSource verifiedClawHub registry

agent-behavior-baseline

Establish an observable baseline for an AI agent before changing it: a minimal SQLite trace store, a fixed eval suite with stable IDs, real-task wiring, a memory retrieval baseline, and an adherence eval with constraint cards. Use when adding observability, measuring whether a change improved behaviour, or deciding between an index and a knowledge graph. Tool-agnostic; stdlib only.

Identity and source

Publisher attributioncengcengcai-creatorregistry owner unverified by skillvetai
Functional categoryAgent Engineering, Security & Governanceautomatically inferred · 70% rule confidence
Package forminstruction with code8 recorded files
Canonical sourceClawHub registryclawhub:cengcengcai-creator:agent-behavior-baseline
Open canonical source ↗

Platform declarations

These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.

OpenClawnative officialProvenance: registry distribution

Independent structural checks

These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.

Claude Codepasses structure
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 11/8/2026.claude/skills/agent-behavior-baseline

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenAI Codexpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+codex-docs-2026-08-13 · 11/8/2026.agents/skills/agent-behavior-baseline

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenClawpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+openclaw-docs-2026-08-13 · 11/8/2026skills/agent-behavior-baseline

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

Installation and inspection

This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.

clawhub install @cengcengcai-creator/agent-behavior-baseline
clawhub inspect @cengcengcai-creator/agent-behavior-baseline --version 1.0.0

Security evidence

SkillVetAI static result: high signal

This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.

Status
completed
Coverage
full text content
Files
8 / 8 inspected as text
Checked
11/8/2026, 5:59:45 AM
Scanner
0.1.3
Policy
1.0.3
1 automated finding
highDynamic code or shell execution is presentscripts/eval_suite.py:27 · confidence 78%subprocess.run(t["cmd"], shell=True
1 High/Critical review queue entry
STATIC_DYNAMIC_CODE_EXECUTIONpending
Open human review queue →
4 inferred permission indicators
  • shell execution — automatically inferred
  • network access — automatically inferred
  • filesystem write — automatically inferred
  • credential access — automatically inferred
1 dependency and API indicators
  • api: clawhub.ai
External clawhub result: suspicious

This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.

Evidence checked
11/7/2026, 3:24:22 PM
Release binding
Matches this record
  • skillspector: suspicious
  • llm: suspicious

Recorded files

The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.

Package content hashsha256:10376f0d09cb210aae7dc532771182095be5220d170f2fe2e573d642853213d5
Show up to 8 recorded paths
  • examples/tasks.json
  • LICENSE
  • README.md
  • references/adherence-eval.md
  • scripts/eval_suite.py
  • scripts/trace_store.py
  • skill-card.md
  • SKILL.md

Source changelog

- Added a tool-agnostic baseline workflow for measuring agent behavior before and after changes. - Defined a minimal SQLite trace store and fixed eval suite with stable IDs. - Added guidance for wiring a real task, measuring memory retrieval, and evaluating rule adherence. - Clarified how to separate environment smoke checks from quality results and when to consider a knowledge graph.