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/cwinvestments/memstack/familiarnpx skills add cwinvestments/memstack --skill familiargit clone --depth 1 https://github.com/cwinvestments/memstackWhat 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 | $0.00028 | $0.00523 |
| Opus 5 | $0.00014 | $0.00262 |
| Sonnet 5 | $0.00006 | $0.00105 |
| Haiku 4.5 | $0.00003 | $0.00052 |
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 2d 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 — 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)
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.
- 2d ago First seen · 69 lines · 28 tokens per session scan A a4209c4e1b7d
familiar is a skill published in the GitHub repository cwinvestments/memstack (417 stars, last pushed 5d ago), licensed MIT. It adds 28 tokens to every session and 523 once invoked, about $0.0001 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
plan-ceo-review
CEO/founder-mode plan review. Rethink the problem, find the 10-star product, challenge premises, expand scope when it creates a better product. Four modes: SCOPE EXPANSION (dream big), SELECTIVE EXPANSION (hold scope + cherry-pick expansions), HOLD SCOPE (maximum rigor), SCOPE REDUCTION (strip to essentials). Use when…
ship
Ship workflow: detect + merge base branch, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, and create a PR. Use for an explicit /ship invocation or when the user requests the full ship, release, or deploy workflow. For an ordinary commit, push, or pull-request publishing request, use the built-in…
design-review
Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them. Iteratively fixes issues in source code, committing each fix atomically and re-verifying with before/after screenshots. For plan-mode design review (before implementation), use…
plan-eng-review
Eng manager-mode plan review. Lock in the execution plan — architecture, data flow, diagrams, edge cases, test coverage, performance. Walks through issues interactively with opinionated recommendations. Use when asked to "review the architecture", "engineering review", or "lock in the plan". Proactively suggest when…
pre-landing-review
Pre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust boundary violations, conditional side effects, and other structural issues. Use when explicitly asked for the specialized pre-landing workflow. Product /review requests are handled by BitFun's unified Review mechanism instead.…
autoplan
Auto-review pipeline — reads the full CEO, design, eng, and DX review skills from disk and runs them sequentially with auto-decisions using 6 decision principles. Surfaces taste decisions (close approaches, borderline scope, codex disagreements) at a final approval gate. One command, fully reviewed plan out. Use when…