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。
开发与测试

discover-feature-flags

Audit Harness FME feature flags across a project. Read-only; never writes. Four modes: inventory (list flags with metadata), rollout-report (per-env rollout state with stalled-promotion detection across a confirmed env sequence), stale-audit (find flags with no impressions via lastImpressionAt), pattern-search (find flags whose rule conditions structurally match an attribute name, matcher type, literal value, segment reference, or flag dependency — not a text grep). Use when asked to "show me all flags", "which flags are stale", "what flags are rolled out", "flag inventory", "flag health", "cleanup candidates", "find flags targeting segment X", "which flags depend on flag Y", or "find flags with rule matching attribute Z". Do not use for single-flag deep dive (explain-flag), creating flags (create-feature-flag), updating targeting (update-flag-targeting), archiving/deleting (manage-flag-lifecycle), pipeline rollouts (fme-pipeline), or code removal (cleanup-feature-flags).

Harness · 已有静态检查记录

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 harness/harness-skills --skill discover-feature-flags

技能说明


name: discover-feature-flags description: >- Audit Harness FME feature flags across a project. Read-only; never writes. Four modes: inventory (list flags with metadata), rollout-report (per-env rollout state with stalled-promotion detection across a confirmed env sequence), stale-audit (find flags with no impressions via lastImpressionAt), pattern-search (find flags whose rule conditions structurally match an attribute name, matcher type, literal value, segment reference, or flag dependency — not a text grep). Use when asked to "show me all flags", "which flags are stale", "what flags are rolled out", "flag inventory", "flag health", "cleanup candidates", "find flags targeting segment X", "which flags depend on flag Y", or "find flags with rule matching attribute Z". Do not use for single-flag deep dive (explain-flag), creating flags (create-feature-flag), updating targeting (update-flag-targeting), archiving/deleting (manage-flag-lifecycle), pipeline rollouts (fme-pipeline), or code removal (cleanup-feature-flags). metadata: author: Harness version: 1.3.0 mcp-server: harness-mcp license: Apache-2.0 compatibility: Requires the Harness MCP server or the Harness CLI

Discover Feature Flags

Audit Harness FME feature flags across a project: list all flags with metadata, show rollout status per environment, find stale flags, or search rule conditions structurally. Read-only. Never writes. Related: explain-flag (single flag), cleanup-feature-flags (code removal), manage-flag-lifecycle (archive).

Tools

Works through the Harness MCP server or the Harness CLI; names are from tool-map.md.

OperationMCPCLI
List environmentsharness_list · fme_environment · filters: { offset: 0, limit: 100 } · compact: falseharness list fme_environment --json
List rollout statusesharness_list · fme_rollout_status · filters: { offset: 0, limit: 100 } · compact: falseharness list rollout_status --json
List flagsharness_list · fme_feature_flag · size: 50 · filters: { name?, tags?, rollout_status_id?, offset? } · compact: falseharness list feature_flag [--search <name>] [--status <ACTIVE|ARCHIVED>] --limit 50 --json
Get flagharness_get · fme_feature_flag · params.feature_flag_nameharness get feature_flag <name> --json
List definitionsharness_list · fme_feature_flag_definition · params.feature_flag_name · filters: { offset: 0, limit: 100 } · compact: falseharness list feature_flag:definition <name> --json
List segmentsharness_list · fme_segment · filters: { segment_type, status?, offset: 0, limit: 100 } · compact: falseharness list segment --segment-type <STANDARD|LARGE|RULE_BASED> --json; cover ACTIVE and ARCHIVED with declared status filters
List experimentsharness_list · fme_experiment · filters: { parent_type: "FEATURE_FLAG", parent_name, status: ["ACTIVE", "PAUSED"], offset: 0, limit: 100 } · compact: falseharness list experiment --parent-type FEATURE_FLAG --parent-name <name> --status ACTIVE --json, then again with --status PAUSED

For each filter: apply it server-side if declared by the installed transport (verify via --help); otherwise fetch the complete inventory and filter client-side. Paginate every list to completion per tool-map.md.

Output

Fixed shape per mode:

Inventory: | Flag | Traffic type | Status | Rollout status | Tags | Owners | Created | Updated |

Rollout report: | Flag | <Env 1>* | <Env 2>* | … | Promotion | Notes | (production envs *; cells use actual treatment names/percentages, killed→<fallback>, targeted, limited, missing, unknown or archived). Promotion: stalled?, ahead, ok, behind (no alert), divergence, both killed, missing, unknown, intended ✓, not comparable, archived, or — for neutral-only. Label each hop in multi-env chains; see promotion-check.md.

Stale audit: | Flag | Bucket | Last Impression Per Env | Config | Next Step | (buckets: stale / active / unknown / never evaluated; verdicts: ready / caution / blocked)

Pattern search: | Flag | Env | Rule # | Combiner | Negated | Matcher type | Predicate match | Status | Notes | (coverage footer: matched N / no-match M / unparsed P / unchecked U; see rule-patterns.md)

Summary: counts per class, truncation line if paginated, hand-offs to sibling skills.

Instructions

Phase 1: Establish scope

Follow scope-establishment.md. Restate: Working in org=..., project=....

Phase 2: Collect inputs

Ask only for missing items relevant to the user's goal:

  • Mode: inventory (default) / rollout-report / stale-audit / pattern-search. Infer from prompt.
  • Filters: name substring, tag, rollout status name, traffic type, status (ACTIVE / ARCHIVED), owner — apply server-side where declared; client-side otherwise on the complete inventory.
  • Environment subset (rollout-report / stale-audit / pattern-search): default all.
  • Staleness threshold (stale-audit only): default 30 days per concepts.md.
  • Pattern-search predicates: collect per rule-patterns.md §Clarification.
  • Promotion check: both the environment sequence and intended target treatment must be confirmed before promotion classifications; otherwise show neutral differences. See promotion-check.md §Inputs.

Phase 3: List environments and rollout statuses

List environments through every page: ID → { name, isProduction }. Default display order: non-production first, production last. **The environment sequence for

阅读完整来源 ↗