跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
安全

night-market-config-catalog

Catalog every config axis, its defaults and guards. Use when adding or auditing configuration. Do not use for running gates; use night-market-operations.

athola · 已有 AI 审核记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add athola/claude-night-market --skill night-market-config-catalog

技能说明


name: night-market-config-catalog description: Catalog every config axis, its defaults and guards. Use when adding or auditing configuration. Do not use for running gates; use night-market-operations.

Night Market Config Catalog

Every configuration axis in this repo: where it lives, what the options and defaults are, whether it is production policy or an experimental opt-in, and what guards it. Flags drift, so every axis ends with a one-line re-verification command. Run it before trusting a value stated here.

Terms used once, defined once:

  • Axis: one independently tunable configuration surface (a file, a key, or an environment variable).
  • Guard: the mechanism that notices when the axis breaks or drifts (a test, a pre-commit hook, a CI job, or a script).
  • Shadow mode: a hook that evaluates and warns but does not block. The blocking posture is opt-in.

Axis table

SurfaceFileKey options and defaultsStatusGuarded by
Quality gate thresholds.claude/quality_gates.jsonenforce_blocking true, max_critical_issues 3, max_warnings_per_dimension 5; per-dimension keys belowProduction policyDocumented in docs/quality-gates.md; consumed as policy prose by sanctum PR workflows (see caveat below)
Context governance.claude/context_governance.jsonenforce_strict_limits false, require_progressive_disclosure true, require_modular_structure true, require_optimization_level "standard", block_on_critical_violations false, max_violations_per_file 5Production, advisorydocs/quality-gates.md
Repo Claude settings.claude/settings.jsonContains only a description key. NO hooks registered at repo level; all active hooks ship from pluginsProduction invariantConvention; see night-market-architecture-contract
Behavioral rules.claude/rules/*.md (8 files)bounded-discovery, markdown-formatting, plan-before-large-dispatch, prefer-invariants-over-fallbacks, prefer-rg-over-grep, shared-utility-consumer-rule, skill-exit-criteria, slop-scan-for-docsProductionslop CI, pre-commit, review practice
Python toolchainroot pyproject.tomlSee "Root pyproject tool tables" belowProductionPre-commit hooks, typecheck.yml, security.yml
Per-plugin coverageplugins/*/pyproject.toml [tool.nightmarket]coverage_threshold = 90 in 19 plugins, 85 in gauntlet (20 files total)ProductionRead by scripts/run-plugin-tests.sh
Pre-commit pins.pre-commit-config.yamlRemote pins: pre-commit-hooks v6.0.0, bandit 1.8.6 (last release supporting the 3.9 system interpreter). Ruff runs from a local repo via the uv-managed binary so hook and make format share one versionProductionscripts/check_pinned_versions.py, python39-compat.yml
Plugin manifest trioplugins/<p>/.claude-plugin/plugin.json, .claude-plugin/metadata.json, openpackage.ymlAll three carry version in lockstep with the marketplace (1.9.15 at compile time)Productionplugins/sanctum/scripts/update_versions.py, plugins/abstract/scripts/validate_plugin.py
Marketplace version.claude-plugin/marketplace.json top-level versionSingle ecosystem version, source of truth for the fan-outProductionupdate_versions.py <version> bumper
MCP servers.mcp.jsonOne stdio server: markitdown via uvx markitdown-mcpProductionManual
LSP config.cclsp.jsonpylsp for py/pyi; typescript-language-server for js/ts and markdownProductionManual
Feature-review scoring.feature-review.yamlversion: 1; weight tables for value and cost; thresholds high_priority 2.8, medium_priority 1.8, confidence_warning 0.6ProductionConsumed by imbue:feature-review
Egregore runtime config.egregore/config.json (runtime file, created in the target repo, not committed here)Nested dataclasses in plugins/egregore/scripts/config.py: overseer, alerts, pipeline, budget, discussions. pipeline.completion_integrity = FalseExperimental opt-in flag inside production configUnit tests in plugins/egregore/tests/test_config.py (default, roundtrip, and raw-JSON opt-in paths)
Conjure delegation~/.claude/hooks/delegation/config.json (runtime file, per machine, not committed here)Top-level enabled defaults to on when absent; only an explicit false opts out. services overrides per-provider ServiceConfig fieldsProduction, default-onplugins/conjure/tests/scripts/test_delegation_executor.py::TestDelegationIsOnUnlessRefused
Herald Stop-hook judgeplugins/herald/hooks/hooks.json + env varsStop hook double_shot_latte.py registered with timeout: 10; internal LLM_TIMEOUT_SECONDS = 8Hook production, LLM path experimentalGuard test asserts LLM timeout stays under the registered hook budget

Caveat on the two .claude/*.json policy files: no Python script in the repo reads them directly. They are policy inputs referenced by docs/quality-gates.md and by sanctum command prose (prepare-pr, pr-review configuration). Treat them as contract documents for review workflows, not as runtime config a daemon loads. Direct programmatic consumers: none found at compile time (candidate: wire one before tightening values).

Quality gate dimensions (.claude/quality_gates.json)

Per-dimension keys and defaults:

DimensionKeysBlocks?
performancemax_file_size_kb 20, max_tokens_per_file 5000, max_function_lines 60, max_complexity_score 12No (block_on_violation false)
securityblock_hardcoded_secrets true, block_insecure_functions true, require_input_validation trueYes (block_on_violation true)
maintainabilitymax_technical_debt_ratio 0.3, max_nesting_depth 5No
compliancerequire_plugin_structure true, require_proper_metadata trueNo

Security

阅读完整来源 ↗