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.
npx agentmods add skills/panbanda/omen/audit-flagsnpx skills add panbanda/omen --skill audit-flagsgit clone --depth 1 https://github.com/panbanda/omenWrote 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.
[](https://agentmods.dev/skills/panbanda/omen/audit-flags)<a href="https://agentmods.dev/skills/panbanda/omen/audit-flags"><img src="https://agentmods.dev/badge/skills/panbanda/omen/audit-flags.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00030 | $0.00696 |
| Opus 5 | $0.00015 | $0.00348 |
| Sonnet 5 | $0.00006 | $0.00139 |
| Haiku 4.5 | $0.00003 | $0.00070 |
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 4d 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.
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 |
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.
- 4d ago First seen · 122 lines · 30 tokens per session scan A 36e0dff84f76
audit-flags is a skill published in the GitHub repository panbanda/omen (19 stars, last pushed yesterday), licensed Apache-2.0. It adds 30 tokens to every session and 696 once invoked, about $0.0002 per session on Opus 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.
Other skills, from other repositories
roam
Codebase comprehension via roam-code CLI. Use when exploring codebases, planning modifications, debugging failures, assessing PR risk, or checking architecture health. Triggers on: understanding project structure, pre-change safety checks, finding symbols/files, blast radius analysis, affected tests, health scoring…
truecourse-hooks
Install, configure, or remove the TrueCourse pre-commit hook.
truecourse-analyze
Run TrueCourse architecture analysis on this repository.
truecourse-fix
Fix TrueCourse violations that have suggested fixes.
truecourse-list
List TrueCourse violations found in this repository.
rspec
This skill should be used when the user asks to "write specs", "create spec", "add RSpec tests", "fix failing spec", or mentions RSpec, describe blocks, it blocks, expect syntax, test doubles, or matchers. Should also be used when editing spec.rb files, working in spec/ directory, planning implementation phases that…