claude-config-verification
Use when modifying the goldband config repo across Claude Code or Codex assets (`skills/`, `hooks/`, `commands/`, `rules/`, `claude/`, `.claude-plugin/`…
Skill by leo110047
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/leo110047-claude-config-verification
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: data, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Node.js package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/claude-config-verification
What's inside
- Skill name
claude-config-verification- Description
- Use when modifying the goldband config repo across Claude Code or Codex assets (`skills/`, `hooks/`, `commands/`, `rules/`, `claude/`, `.claude-plugin/`, `.codex/`, `codex/`, or install scripts) and you need a concrete health check before claiming the change is safe. Best fit for config repositories that need JSON/TOML validation, hook reference checks, Codex rule validation, plugin-data probing, and optional router replay.
- License
- MIT
- Instructions
- 64 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Agent Skills spec issues
- allowed-tools: must be a space-separated string
Files (8)
- SKILL.md
- verification-report-template.md · assets/
- probe-plugin-data.js · scripts/
- verify-claude-config-codex.js · scripts/
- verify-claude-config-history.js · scripts/
- verify-claude-config-output.js · scripts/
- verify-claude-config-runtime.js · scripts/
- verify-claude-config.js · scripts/
SKILL.md (first lines)
# goldband Config Verification
## When to Use
- After changing hook router logic or hook policies
- After changing Claude/Codex global templates, execpolicy rules, or portable-skill install logic
- After editing `hooks/hooks.json`, `skill-rules.json`, or `.claude-plugin/plugin.json`
- After editing `.codex/config.toml`, `codex/config.toml`, `codex/rules/default.rules`, or `AGENTS.md`
- After adding/removing skills, commands, or rules
- Before claiming the goldband Claude/Codex config repo is ready to ship
- Before depending on `${CLAUDE_PLUGIN_DATA}` for persistent plugin state
## Scripts
Scripts live next to this skill in `./scripts/`. From the goldband repo root,
use `skills/global/claude-config-verification/scripts/...`.
- `./scripts/probe-plugin-data.js`
- Confirms whether `${CLAUDE_PLUGIN_DATA}` is available in the current runtime
- Verifies the target directory can be created, written, and read back
- Falls back to temp storage when the current execution context does not expose plugin data
- `./scripts/verify-claude-config.js`
- Validates JSON and TOML files
- Checks `SKILL.md` frontmatter and linked reference files
- Verifies hook script references in `hooks/hooks.json`
- Verifies required Codex repo files exist
- Runs `codex execpolicy check` against `codex/rules/default.rules` when the `codex` CLI is available
- Records a verification history entry in stable plugin data when available
- `./scripts/verify-claude-config.js --router-replay`
- Runs the hook router replay harness when router behavior changed
## Gotchas
- `${CLAUDE_PLUGIN_DATA}` may be absent outside plugin hook execution; scripts then fall back to temp storage.
- Stale hook references and broken reference links block shipping as much as invalid JSON.
- Do not claim Codex support is safe if `codex/rules/default.rules` has not been syntax-checked against real commands.
- Do not claim router changes are safe without replay when router policy code changed.
- Do not add a new global skill without also updating installer profiles and inventory documentation.
- Do not change shared policy text without checking both the Claude adapter (`rules/`, `hooks/`) and the Codex adapter (`AGENTS.md`, `codex/rules/`).
- `SKILL.md` names every script and asset the skill bundles.
## Memory and Reports
- Verification history is appended to `history.jsonl`
- Storage: `${CLAUDE_PLUGIN_DATA}/claude-config-verification/`, else the system temp directory
- Report template: `assets/verification-report-template.md`
## Suggested Workflow
1. Run `node skills/global/claude-config-verification/scripts/probe-plugin-data.js`
2. Run `node skills/global/claude-config-verification/scripts/verify-claude-config.js`
3. If hooks/router changed, run `node skills/global/claude-config-verification/scripts/verify-claude-config.js --router-replay`
4. Summarize results using `assets/verification-report-template.md`
## Completion Check
Before claiming config verification is complete, report:
- Which script was run and with what target surface.
- Whether the report file or history entry was produced.
- Any missing binary, plugin data path, runtime state, or install surface.
- Whether the evidence proves full parity or only partial verification.From leo110047/goldband, MIT.
More from leo110047/goldband
- 0.566score
freeze-mode
leo110047
Use when you need a read-only investigation window for production or sensitive systems and want Claude blocked from non-read-only tools plus non-read-only…
SkillAFreshness: AClaude Code +9 - 0.563score
goldband
leo110047
Route Goldband tasks through the formal capability interface for review, investigation, QA, planning, browser, design, safety, context, knowledge…
SkillAFreshness: AClaude Code +9 - 0.563score
careful-mode
leo110047
Use before running destructive or prod-facing CLI commands.
SkillAFreshness: AClaude Code +9 - 0.560score
subagent-development
leo110047
Use when a task can be isolated into a fresh-context subagent or parallelized safely, and its result needs review against the original requirements.
SkillAFreshness: AClaude Code +9 - 0.560score
security-checklist
leo110047
Use when working on authentication, authorization, input validation, secret handling, sensitive data storage, API hardening, deployment security, or security…
SkillAFreshness: AClaude Code +9 - 0.560score
ci-cd-integration
leo110047
Use when setting up or changing CI pipelines, GitHub Actions workflows, build/test/deploy gates, release automation, CI secrets handling, or build caching.
SkillAFreshness: AClaude Code +9 - 0.560score
planning-workflow
leo110047
Use when turning a request into an implementation plan, especially before multi-file changes, refactors, or work that needs explicit phases and verification.
SkillAFreshness: AClaude Code +9 - 0.560score
frontend-design
leo110047
Use when creating, restyling, or reviewing frontend pages, components, dashboards, tools, posters, artifacts, or application screens.
SkillAFreshness: AClaude Code +9 - 0.560score
evidence-based-coding
leo110047
Ground code, configuration, and completion claims in evidence for the current candidate and relevant environment.
SkillAFreshness: AClaude Code +9 - 0.560score
performance-optimization
leo110047
Use for slowness or memory pressure, performance claims, and changes to bulk processing, materialization, caching, or parallel execution where workload growth…
SkillAFreshness: AClaude Code +9 - 0.560score
prompt-hygiene
leo110047
Use when creating or editing prompts, system prompts, agent instructions, workflow prompts, cron prompts, briefing prompts, design-tool prompts…
SkillAFreshness: AClaude Code +9 - 0.556score
skill-developer
leo110047
Use when creating, merging, or editing portable skills, trigger descriptions, progressive-disclosure layouts, or hook-backed skill tooling in this repo.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 5
- Last commit (this folder)
- Oct 14, 2026 (14 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/leo110047/goldband
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from leo110047
- 0.566score
freeze-mode
leo110047
Use when you need a read-only investigation window for production or sensitive systems and want Claude blocked from non-read-only tools plus non-read-only…
SkillAFreshness: AClaude Code +9 - 0.563score
careful-mode
leo110047
Use before running destructive or prod-facing CLI commands.
SkillAFreshness: AClaude Code +9 - 0.563score
goldband
leo110047
Route Goldband tasks through the formal capability interface for review, investigation, QA, planning, browser, design, safety, context, knowledge…
SkillAFreshness: AClaude Code +9 - 0.560score
subagent-development
leo110047
Use when a task can be isolated into a fresh-context subagent or parallelized safely, and its result needs review against the original requirements.
SkillAFreshness: AClaude Code +9 - 0.560score
ci-cd-integration
leo110047
Use when setting up or changing CI pipelines, GitHub Actions workflows, build/test/deploy gates, release automation, CI secrets handling, or build caching.
SkillAFreshness: AClaude Code +9 - 0.560score
planning-workflow
leo110047
Use when turning a request into an implementation plan, especially before multi-file changes, refactors, or work that needs explicit phases and verification.
SkillAFreshness: AClaude Code +9
Cite this page
claude-config-verification skill. Agent Mart. https://agentmart.dev/skills/leo110047-claude-config-verification (last updated 2026-10-24)