feature-flags-authoring

feature-flags-authoring is a skill for Claude Code, Codex from PackmindHub/packmind. It costs 98 tokens per session (1,492 once invoked), scanned A, original, Apache-2.0.

A developer guide for managing Packmind feature flags, which turn features on or off for selected email addresses or domains.

In plain words
What is it for?
Use it to create, edit, restrict, open, retire, or remove a Packmind feature flag.
Why use it?
It keeps the same flag rules consistent across the frontend and backend and shows where each change must be made.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/packmindhub/packmind/feature-flags-authoring
Any agent
npx skills add PackmindHub/packmind --skill feature-flags-authoring
Clone the repo
git clone --depth 1 https://github.com/PackmindHub/packmind

Made for: Claude Code, Codex.

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.

agentmods badge for feature-flags-authoring

README.md
[![agentmods](https://agentmods.dev/badge/skills/packmindhub/packmind/feature-flags-authoring.svg)](https://agentmods.dev/skills/packmindhub/packmind/feature-flags-authoring)
Your own site
<a href="https://agentmods.dev/skills/packmindhub/packmind/feature-flags-authoring"><img src="https://agentmods.dev/badge/skills/packmindhub/packmind/feature-flags-authoring.svg" alt="Measured on agentmods" height="20"></a>
Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,492 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00098 $0.01492
Opus 5 $0.00049 $0.00746
Sonnet 5 $0.00020 $0.00298
Haiku 4.5 $0.00010 $0.00149

Measured 3d ago against content hash 83b4e61e8001, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

feature-flags-authoring 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 3d 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.

.claude/skills/feature-flags-authoring/SKILL.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Feature Flags Authoring

A developer how-to for the full lifecycle of a Packmind feature flag: add, edit, remove. Flags gate a feature by email domain (or exact email). The same decision function runs on frontend and backend, so behavior never diverges. Follow the steps below exactly — every flag touches three places.

For inventorying existing flags, orphan detection, and audience audits, use the feature-flags-audit skill instead. This skill changes flags; that one scans them.

Where things live

  • Shared registry — @packmind/feature-flags (pure, env:shared, browser-safe). The single source of truth:
    • registry.ts — the *_FEATURE_KEY constants, DEFAULT_FEATURE_DOMAIN_MAP (Record<string, readonly string[]> mapping each flag's string value to allowed entries), and the FeatureFlagKey union.
    • isFeatureFlagEnabled.ts — the pure evaluator: isFeatureFlagEnabled({ featureKeys, featureDomainMap, userEmail }).
  • Frontend gate<PMFeatureFlag> from @packmind/ui (or a direct isFeatureFlagEnabled(...) call). The keys, DEFAULT_FEATURE_DOMAIN_MAP, and isFeatureFlagEnabled are re-exported from @packmind/ui for back-compat, so existing consumers can import from either place.
  • Backend gateisFeatureEnabled(flag, { userEmail }), a plain async helper from @packmind/node-utils. It resolves the env kill-switch first, then defers to the shared email-domain rule. It is NOT a port and has no DI — import it and call it.
  • Env kill-switchFF_<SCREAMING_SNAKE> (e.g. FF_CHANGE_PROPOSALS_IN_WEBAPP). on/all/true force the flag on; off/none/false force it off; unset or empty falls through to the email-domain map.

Two flags exist today: 'change-proposals-in-webapp' and 'orga-space-management'.

Add a flag

1. Register it in @packmind/feature-flags

Add the key constant, the audience entry, and extend the union. Do all three — a constant with no map entry is never enabled for anyone; a map entry with no union member can't be typed at call sites.

Read the full file on GitHub · 107 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.

  1. 3d ago First seen · 107 lines · 98 tokens per session scan A 83b4e61e8001

Subscribe to this mod's changes

feature-flags-authoring is a skill published in the GitHub repository PackmindHub/packmind (308 stars, last pushed today), licensed Apache-2.0. It adds 98 tokens to every session and 1,492 once invoked, about $0.0005 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.