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.
git clone --depth 1 https://github.com/VaiYav/speckit-product-forgeWrote 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/commands/vaiyav/speckit-product-forge/feature-flag-cleanup)<a href="https://agentmods.dev/commands/vaiyav/speckit-product-forge/feature-flag-cleanup"><img src="https://agentmods.dev/badge/commands/vaiyav/speckit-product-forge/feature-flag-cleanup/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.
<a href="https://agentmods.dev/commands/vaiyav/speckit-product-forge/feature-flag-cleanup"><img src="https://agentmods.dev/badge/commands/vaiyav/speckit-product-forge/feature-flag-cleanup.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00112 | $0.01965 |
| Opus 5 | $0.00056 | $0.00983 |
| Sonnet 5 | $0.00022 | $0.00393 |
| Haiku 4.5 | $0.00011 | $0.00197 |
Grade A, and why
speckit.product-forge.feature-flag-cleanup 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 10d 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 — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Forge — Feature Flag Cleanup
You are the Flag Archivist for Product Forge. Your job: find feature flags whose time is up — they have been fully rolled out, the experiment has ended, or the team forgot about them — and produce an actionable cleanup plan.
This command is cross-cutting (not a phase) and read-only unless the user explicitly approves the removal plan.
User Input
$ARGUMENTS
Parse for:
--feature=<slug>— optional scope to a single feature.--after=<ISO date>— override "today" as the stale threshold (useful for dry-runs).--include-non-registry— also scan the codebase for flags not tracked in anyflags/registry.yml.
Step 0: Load Config
Read .product-forge/config.yml → features_dir, codebase_path.
Step 1: Gather Flag Registry
Enumerate feature roots via the Path-Resolution Contract enumerate()
(docs/runtime.md §12.3) and
collect each root's flags/registry.yml (depth-tolerant over flat and
domain-nested; the old {features_dir}/*/flags/ glob only saw flat features).
Build a unified view:
| Flag key | Feature | Default | Owner | cleanup_after | Source file |
|---|---|---|---|---|---|
new_onboarding |
onboarding-v2 | off | @alice | 2026-03-01 | features/onboarding-v2/flags/registry.yml |
| ... |
If no registries exist, report: "No registered flags found. If your
project has flags not registered through release-readiness, re-run with
--include-non-registry to scan the codebase."
Step 2: Classify Each Flag
For every flag, classify into one of:
| Class | Criteria |
|---|---|
| Stale | cleanup_after < today (or --after override). |
| Approaching | cleanup_after ≤ today + 14 days. |
| Active | cleanup_after > today + 14 days OR not set. |
| Orphan | In codebase but not in any registry (requires --include-non-registry). |
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.
- 10d ago First seen · 234 lines · 112 tokens per session scan A fb62c979001c
speckit.product-forge.feature-flag-cleanup is a command published in the GitHub repository VaiYav/speckit-product-forge (23 stars, last pushed 17d ago), licensed MIT. It adds 112 tokens to every session and 1,965 once invoked, about $0.0006 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 commands, from other repositories
qa-changes
This skill should be used when the user asks to "QA a pull request", "test PR changes", "verify a PR works", "functionally test changes", or when an automated workflow triggers QA validation of code changes. Provides a structured methodology for setting up the environment, exercising changed behavior, and reporting…
doctor
Diagnosticar y reparar problemas del framework Don Cheli, git y entorno. Usa cuando el usuario dice "doctor", "problemas del framework", "don cheli no funciona", "repair Don Cheli", "debug setup", "setup broken", "framework broken", "reparar entorno". Detecta y repara issues de configuración, git y dependencias…
fix
Universal debugging and fix application with semantic code analysis.
doctor
Badi configuration validation. Checks all Badi components and produces a diagnostic report.
http-service
Build, review or debug a Bun HTTP service. Loads the http-service skill, then works the task through its workflow.
gh-issue-use-cypress
Like /gh-issue-use-browser, but pinned to the Cypress MCP — use when your project runs the Cypress MCP for browser automation. Example — /gh-issue-use-cypress "Composer > Save" saving toasts failure but the record persists.