A procedure for finding old feature flags and deciding which ones should be removed. Feature flags are switches that turn software behavior on or off.

Listing flags, checking their owners, finding related files, and prioritizing cleanup based on age, spread, and flag type.

Old flags make code harder to understand and maintain, especially after a launch or experiment has finished.

audit-flags — Skill for Claude Code by panbanda/omen

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add panbanda/omen --skill audit-flags

Clone the repo

git clone --depth 1 https://github.com/panbanda/omen

Made for: Claude Code.

Or install omen-development, the plugin that ships this one along with the rest of its 13 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/panbanda/omen/audit-flags/github.svg)](https://agentmods.dev/skills/panbanda/omen/audit-flags)

Your own site

<a href="https://agentmods.dev/skills/panbanda/omen/audit-flags"><img src="https://agentmods.dev/badge/skills/panbanda/omen/audit-flags/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/panbanda/omen/audit-flags"><img src="https://agentmods.dev/badge/skills/panbanda/omen/audit-flags.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 696 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00030	$0.00696
Opus 5.5	$0.00012	$0.00278
Sonnet 5.5	$0.00006	$0.00139
Haiku 4.5	$0.00003	$0.00070

Measured 1mo ago against content hash 36e0dff84f76, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

audit-flags scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/development/skills/audit-flags/SKILL.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Audit Flags

Identify stale feature flags and provide actionable cleanup recommendations.

Prerequisites

Omen CLI must be installed and available in PATH.

Workflow

Step 1: Detect All Flags

Run the flags analysis:

omen -f json flags

Returns all feature flag references with staleness information, grouped by provider.

Step 2: Identify Ownership

Run the ownership analysis:

omen -f json ownership

Determine who owns the code containing flags - they should own cleanup.

Step 3: Check Coupling

Run the temporal coupling analysis:

omen -f json temporal

Find files that change together with flag-containing files.

Flag Lifecycle Reference

Flag Type	Expected Lifespan	Action if Stale
Release	7-14 days	Remove after 100% rollout
Experiment	30-90 days	Remove after analysis complete
Ops/Kill Switch	Permanent	Document, don't remove
Permission	Permanent	Document, audit access

Priority Matrix

Priority	Criteria	Action
CRITICAL	>90 days stale, high file spread	Immediate removal
HIGH	>60 days stale or in hotspot files	This sprint
MEDIUM	>30 days stale	Next sprint
LOW	Recently added or low file spread	Monitor

Output Format

Generate a flag audit report:

# Feature Flag Audit Report

## Summary

| Metric | Count |
|--------|-------|
| Total flags | 23 |
| Stale (>30 days) | 8 |
| Critical priority | 2 |
| High priority | 3 |

## Stale Flags (Action Required)

### `enable_new_checkout` (CRITICAL)
- **Provider**: LaunchDarkly
- **Age**: 95 days
- **References**: 12 across 5 files
- **Owner**: alice (payment team)
- **Action**: Remove - likely at 100%

### `experiment_pricing_v2` (HIGH)
- **Provider**: Split
- **Age**: 67 days
- **References**: 4 across 2 files
- **Owner**: bob (growth team)
- **Action**: Check experiment results, then remove

## Cleanup Roadmap

### This Sprint
1. Remove `enable_new_checkout` - 2 hours
2. Investigate `experiment_pricing_v2` - 1 hour

### Next Sprint
1. Clean up remaining HIGH priority flags

## Permanent Flags (Document)

| Flag | Type | Purpose |
|------|------|---------|
| `kill_switch_payments` | Ops | Emergency disable |
| `beta_access` | Permission | Feature gating |

Read the full file on GitHub · 122 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

1mo ago First seen · 122 lines · 30 tokens per session scan A 36e0dff84f76

Subscribe to this mod's changes

audit-flags is a skill published in the GitHub repository panbanda/omen (20 stars, last pushed today), licensed Apache-2.0. It adds 30 tokens to every session and 696 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Claude Code Project management claude-plugins mcp-server static-analysis tech-debt vibe-coding

agent-notes

Use when deciding whether a Cherry Studio change needs an Agent Note, authoring or reviewing a Spec, recording a durable bug-fix decision, moving a note between proposed/implemented/rejected, or checking supersession and stacked Spec approval.

CherryHQ/cherry-studio · 51 tokens

meeting-to-deal

Turn meeting transcripts into deal updates — key points, commitments, and next steps posted to matching CRM deals automatically. Auto-creates contacts for new attendees. Use when someone says "log my meetings to deals", "update CRM from calls", "what did I commit to in meetings", "sync notetaker", "log this meeting"…

mondaycom/mcp · 107 tokens

memstack-product-roadmap-builder

Use this skill when the user says 'roadmap', 'product roadmap', 'quarterly plan', 'now/next/later', 'OKRs', or needs strategic planning with themes, milestones, resource allocation, and stakeholder-ready views. Do NOT use for MVP scoping or sprint-level planning.

cwinvestments/memstack · 67 tokens

audit-flags