Optimizes or restructures CLAUDE.md/AGENTS.md with progressive disclosure and zero information loss. Use when the user asks to optimize, audit, 精简/瘦身/重构, or split instruction files, asks for their best practices (最佳实践), sees Memory files taking a large share of /context, reports rules in instruction files being ignored, or a task starts moving instruction sections. Not for generic task drift unless instruction files are in scope; not for moving memory entries into docs (use claude-code-ops-router).
- Stars
- 1,540
- Version
- v2
- Copies
- 0
Overview
Waxell rates it high risk: 22 findings, highest severity high.
- Highest severity
- high
- Findings
- 22
- What ran
- Static analysis + deep scan
A clean result means nothing alarming in what is published, not a guarantee. How the checks work
We don't republish the skill's instructions. Read them on GitHub at the reviewed commit.
Security
Security scan
Checked yesterday
Result
High risk Waxell rates it high risk: 22 findings, highest severity high.
Checked with static analysis + deep scan: servers it launches, packages it installs at runtime, scripts piped to a shell and bundled binaries. The deep scan also read the instructions for prompt injection and data exfiltration. Nothing was run. How the checks work
Findings (22)
high · 20
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:31 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:175 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:250 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:258 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:320 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:334 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:342 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:461 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:471 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:498 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:546 · skillspector:AE1
- high
Agent Snooping: Agent Config Directory Access
SKILL.md:103 · skillspector:AS1
- high
Agent Snooping: Agent Config Directory Access
SKILL.md:103 · skillspector:AS1
- high
Agent Snooping: Agent Config Directory Access
SKILL.md:151 · skillspector:AS1
- high
Agent Snooping: Agent Config Directory Access
SKILL.md:151 · skillspector:AS1
- high
Agent Snooping: Agent Config Directory Access
references/progressive_disclosure_principles.md:34 · skillspector:AS1
- high
Agent Snooping: Agent Config Directory Access
SKILL.md:151 · skillspector:AS1
- high
Tool Misuse: Tool Parameter Abuse
references/progressive_disclosure_principles.md:598 · skillspector:TM1
- high
Agent Snooping: Agent Config Directory Access
references/verification-recipes.md:89 · skillspector:AS1
- high
Tool Misuse: Tool Parameter Abuse
references/verification-recipes.md:108 · skillspector:TM1
medium · 2
- medium
Without declared permissions the skill's intent is opaque and cannot be validated.
SKILL.md:1 · skillspector:LP3
- medium
Dangerous Code Execution: subprocess module call
tests/test_scripts.py:47 · skillspector:AST4
Versions
Version history
Each distinct content we have seen, newest first, with the verdict it got at the time.
- v22026-11-202 changed High riskgot riskier
- v12026-11-03 No issues
Files
Files
7 files, 142 KB in total. Names only; open them on GitHub.
- SKILL.md
- references/progressive_disclosure_principles.md
- references/verification-recipes.md
- scripts/markdown_headings.py
- scripts/profile_claude_md.py
- scripts/sink_sections.py
- tests/test_scripts.py
See and control which skills your people use
Inside your organization, Waxell scans each skill and plugin before anyone installs it, approves what passes and publishes it to a private marketplace, and puts every MCP tool call behind one governed URL.
30 minutes. No commitment.
SOC 2 Type II attested · ISO/IEC 27001:2022 certified · HIPAA with a BAA · aligned to the EU AI Act and NIST AI RMF
More engineering skills and plugins
claude-switch-models-setupdaymadeIsolates profiles for multi-provider setup and switching models in separate terminal windows (Kimi, MiniMax, DeepSeek, GLM, StepFun,… High riskEngineeringAI & agents1.5k
prior-work-retrievaldaymadeOnly for explicit prior-work/reuse/history requests, not status checks. Finds and verifies existing work before new production when reuse… High riskEngineeringAI & agents1.5k
read-codex-historydaymadeReads, searches and exports local OpenAI Codex history without continuing work: session inventory, timelines, verbatim user input, indexed… High riskEngineeringAI & agents1.5k
local-codexdaymadeLaunches and manages the local OpenAI Codex CLI as a non-interactive coding sub-agent via ChatGPT OAuth, never API keys. Use to delegate… High riskEngineeringAI & agents1.5k