A way to split a large coding task into prompts for several parallel coding-agent sessions. It includes shared context, boundaries between tasks, coordination notes, and a suggested merge order.

Use it to plan parallel work on features, bug fixes, migrations, documentation, or other large tasks that can be separated into smaller parts.

It helps divide independent work while reducing conflicting edits and unclear handoffs between sessions.

familiar — Skill for Claude Code by cwinvestments/memstack

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 cwinvestments/memstack --skill familiar

Clone the repo

git clone --depth 1 https://github.com/cwinvestments/memstack

Made for: Claude Code.

Or install memstack, the plugin that ships this one along with the rest of its 87 skills, 2 commands, 6 hooks.

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/cwinvestments/memstack/familiar/github.svg)](https://agentmods.dev/skills/cwinvestments/memstack/familiar)

Your own site

<a href="https://agentmods.dev/skills/cwinvestments/memstack/familiar"><img src="https://agentmods.dev/badge/skills/cwinvestments/memstack/familiar/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/cwinvestments/memstack/familiar"><img src="https://agentmods.dev/badge/skills/cwinvestments/memstack/familiar.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 523 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	$0.00028	$0.00523
Opus 5.5	$0.00011	$0.00209
Sonnet 5.5	$0.00006	$0.00105
Haiku 4.5	$0.00003	$0.00052

Measured 2mo ago against content hash 375a71f5f8aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

familiar 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 2mo 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.

skills/familiar/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

👻 Familiar: Dispatching Sub-Agents...

Break large tasks into coordinated CC session prompts for parallel execution.

Activation

When this skill activates, output:

👻 Familiar: Dispatching sub-agents...

Then execute the protocol below.

Protocol

Analyze the task: identify independent sub-tasks that can run in parallel
Determine session count: split into 2-6 sessions based on complexity
For each sub-task, generate a complete CC prompt that includes:
- Working directory path
- Full task description with acceptance criteria
- Any shared context (database schema, API contracts, types)
- MemStack activation line: Read $MEMSTACK_PATH/MEMSTACK.md
- CC Monitor reporting snippet (if configured in config.json)
Add coordination notes: specify what each session should NOT touch to avoid conflicts
Define merge order: which session's work should be committed first

Inputs

The large task description
Project directory from config.json
Number of available CC sessions (default: 3)

Outputs

Numbered list of sub-task prompts, each ready to paste into a new CC session
Coordination notes explaining dependencies and merge order

Example Usage

User: "dispatch: build the analytics dashboard, API routes, and database migration"

Familiar activates:

👻 Familiar: Dispatching sub-agents...

Session 1, Database & Types
Working directory: C:\Projects\AdminStack
Task: Create migration + TypeScript types for analytics...

Session 2, API Routes
Working directory: C:\Projects\AdminStack
Task: Build /api/analytics endpoints (types from Session 1)...

Session 3, Frontend Page
Working directory: C:\Projects\AdminStack
Task: Build /analytics dashboard page...

Merge order: Session 1 → Session 2 → Session 3

Level History

Lv.1: Base: Multi-agent dispatch with coordinated prompts. (Origin: MemStack v1.0, Feb 2026)
Lv.2: Enhanced: Added YAML frontmatter, activation message, merge ordering. (Origin: MemStack v2.0 MemoryCore merge, Feb 2026)

Read the full file on GitHub · 69 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.

2mo ago Changed 375a71f5f8aa
2mo ago First seen · 69 lines · 28 tokens per session scan A a4209c4e1b7d

Subscribe to this mod's changes

familiar is a skill published in the GitHub repository cwinvestments/memstack (429 stars, last pushed 13d ago), licensed MIT. It adds 28 tokens to every session and 523 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.

Building agents Claude Code Planning ai-coding anthropic claude developer-tools vibe-coding

familiar next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
familiarcwinvestments/memstack	Skill	429	13d ago	MIT	A	28	Claude Code
agent-flutter-developertravisjneuman/.claude	Skill	107	yesterday	MIT	A	74	Claude Code
content-repurposertravisjneuman/.claude	Skill	107	yesterday	MIT	A	43	Claude Code, Codex
electron-desktoptravisjneuman/.claude	Skill	107	yesterday	MIT	A	38	Claude Code, Codex
impact-report-writertravisjneuman/.claude	Skill	107	yesterday	MIT	A	43	Claude Code, Codex
investment-memo-generatortravisjneuman/.claude	Skill	107	yesterday	MIT	A	37	Claude Code, Codex
agent-seo-specialisttravisjneuman/.claude	Skill	107	yesterday	MIT	A	85	Claude Code