Sweep Flag Namespace

Bulk-extract every candidate flag from a binary namespace, build an extraction inventory with occurrence counts and call-type tags, cross- reference against a documented set, and track completeness across probe campaigns until the undocumented remainder reaches zero. Covers namespace prefix harvesting, gate-vs-telemetry disambiguation at the call-site level, completeness metrics, DEFAULT-TRUE population reporting, and a final completion confirmation scan. Use upstream of probe-feature-flag- state when you need a complete catalog rather than a sample, or when a prior wave-based campaign needs a

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add pjt222/agent-almanac --skill sweep-flag-namespace
Manual install
git clone --depth 1 https://github.com/pjt222/agent-almanac.git /tmp/agent-almanac
mkdir -p ~/.claude/skills
cp -r /tmp/agent-almanac/i18n/caveman-lite/skills/sweep-flag-namespace ~/.claude/skills/sweep-flag-namespace

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Sweep Flag Namespace

Exhaustively extract every flag candidate from a binary's namespace, separate gate calls from telemetry, and track completeness against a running documented set until undocumented remainder is zero. Where `probe-feature-flag-state` classifies one flag at a time, this skill produces the catalog those probes operate against — and confirms when the catalog is complete.

## When to Use

- A flag-discovery campaign is mid-flight and you need a verifiable stopping condition rather than guessing whether you have "enough" flags.
- A binary's flag namespace is large (hundreds of candidate strings) and a sample-based approach risks missing meaningful gates.
- You need to report DEFAULT-TRUE flags separately from DEFAULT-FALSE — the high-signal subset of any namespace.
- You are running multi-wave documentation against a binary and want each wave's completion metric in writing.
- You suspect a previous campaign ended prematurely and need to confirm or refute that with a fresh sweep.

## Inputs

- **Required**: binary or bundle file you can read.
- **Required**: namespace prefix (synthetic example: `acme_*`) that identifies flags belonging to the system under study.
- **Required**: working documentation set — running list of flag write-ups your campaign has produced so far.
- **Optional**: gate-reader function names (synthetic: `gate(...)`, `flag(...)`, `isEnabled(...)`) — precomputing these speeds Step 2.
Read the full skill on GitHub

Details

Skill name
sweep-flag-namespace
Path
i18n/caveman-lite/skills/sweep-flag-namespace/SKILL.md
License
MIT
Repo updated
18 November 2026

FAQ

What does the Sweep Flag Namespace skill do?

Bulk-extract every candidate flag from a binary namespace, build an extraction inventory with occurrence counts and call-type tags, cross- reference against a documented set, and track completeness across probe campaigns until the undocumented remainder reaches zero. Covers namespace prefix harvesting, gate-vs-telemetry disambiguation at the call-site level, completeness metrics, DEFAULT-TRUE population reporting, and a final completion confirmation scan. Use upstream of probe-feature-flag- state when you need a complete catalog rather than a sample, or when a prior wave-based campaign needs a

How do I install the Sweep Flag Namespace skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add pjt222/agent-almanac --skill sweep-flag-namespace. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Sweep Flag Namespace popular?

It lives in pjt222/agent-almanac, which has 45 GitHub stars and 4 forks, and is included in 1 curated skill list.

Related skills

Adapt Architecture

45

pjt222/agent-almanac

Execute structural metamorphosis using strangler fig migration, chrysalis phases, and interface preservation. Covers transformation planning, parallel running, progressive cutover, rollback design, and post-metamorphosis stabilization for system architecture evolution. Use when assess-form has classified the system as READY for transformation, when migrating from monolith to microservices, when replacing a core subsystem while dependents continue operating, or when any architectural change must be gradual rather than big-bang.

Software DevelopmentIn 1 list

Adaptic

45

pjt222/agent-almanac

Master skill composing the 5-step synoptic cycle for panoramic synthesis across multiple domains. Orchestrates meditate, expand-awareness, observe, awareness, integrate-gestalt, and express-insight into a coherent process that produces unified understanding rather than sequential compromise. Use when a problem genuinely spans 3+ domains and the interactions between domains matter more than depth in any one, when sequential analysis feels like compromise rather than integration, or before major architectural decisions affecting multiple stakeholders.

OtherIn 1 list

Add Puzzle Type

45

pjt222/agent-almanac

Scaffold a new puzzle type across all 10+ pipeline integration points in jigsawR. Creates the core puzzle module, wires it into the unified pipeline (generation, positioning, rendering, adjacency), adds ggpuzzle geom/stat layers, updates DESCRIPTION and config.yml, extends the Shiny app, and creates a comprehensive test suite. Use when adding a completely new puzzle type to the package or following the 10-point integration checklist to ensure nothing is missed end-to-end.

Testing & QAIn 1 list

Transfer Pricing

43

AlsKozlov/ru-legal

Transfer pricing compliance — Раздел V.1 НК. Identification of controlled transactions, methods (CUP / Resale Price / Cost-Plus / TNMM / Profit Split), Уведомление о контролируемых сделках (до 20 мая след.года), документация по ТЦ. РФ post-2022 — fewer cross-border controlled txns, но domestic пары по-прежнему flagged.

Marketing, Sales & Business

Stakeholder Summary

43

AlsKozlov/ru-legal

Конвертирует длинный юридический review договора в краткое резюме для бизнес-stakeholder'а, который реально его прочитает — не legal memo, а двухминутный ответ "можно подписывать и что мне нужно знать". Используй когда пользователь говорит "сделай резюме для бизнеса", "напиши это для [stakeholder]", "объясни procurement", "non-legal summary", или когда review готов и нужно его отправить кому-то вне юр.отдела.

Marketing, Sales & Business

Vendor Agreement Review

43

AlsKozlov/ru-legal

Reference: review входящего vendor agreement по российскому праву против playbook команды. Флагнёт отклонения, оценит риски, генерирует конкретные redline'ы, и маршрутизирует к нужному approver'у. Учитывает РФ specifics: существенные условия для гл.39 (услуги) / гл.37 (подряд) / §3 гл.30 (поставка), ст.401 п.4 (LoL не работает при умысле), ст.431.2 (заверения) vs ст.406.1 (возмещение потерь), ст.1295 (IP не переходит автоматически), 152-ФЗ (ДОУ), налоговое агентирование. Загружается из `/contract-law:review` когда обнаружен vendor MSA, договор услуг, подряда, или поставки.

Marketing, Sales & Business

Browse the most popular Claude skills, all marketing, sales & business skills, or write your own with the skills generator.