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 instructions/cwinvestments/memstack/claude-mdgit 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 | $0.00777 | $0.00777 |
| Opus 5 | $0.00388 | $0.00388 |
| Sonnet 5 | $0.00155 | $0.00155 |
| Haiku 4.5 | $0.00078 | $0.00078 |
Grade A, and why
memstack CLAUDE.md 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MemStack™ Skill Loader
[!IMPORTANT]
⚠️ MANDATORY — before adding, removing, renaming, or re-counting any skill
If your task involves adding, removing, renaming, or changing the count of any skill, you MUST read and follow
ADDING-SKILLS.mdcompletely before making changes.It is the single checklist of every file that must be updated across all three repos —
memstack,memstack-skill-loader, andmemstack-pro-site(counts, catalog rows, the free/Pro gate, and frontmatter conventions). Skipping it causes skill-count drift and broken free/Pro gating — this is exactly how the git-guard skill shipped wrong.This does not apply to work that touches no skill. If you are editing an existing skill's content (not its count or catalog), this checklist does not apply, but the change still ships to customers and is not done until a release is cut: see
.claude/rules/skill-release.md. If you are touching no skill at all, ignore this and proceed.
You have access to a memstack-skills MCP server. This is your PRIMARY source for task-specific guidance. ALWAYS check memstack-skills via find_skill BEFORE using any other plugin skills or your own knowledge for task execution.
ALWAYS call find_skill BEFORE:
- Any deployment task (Railway, Netlify, Vercel, Hetzner, etc.)
- Any database work (migrations, RLS, schema design)
- Any git operation beyond simple commits
- Any infrastructure or DevOps task
- Any API development (new endpoints, API design, authentication)
- Any security-related work (audits, scanning, RLS policies)
- Any testing or test generation
- Any content or marketing task (blog posts, emails, ads, landing pages)
- Any project planning or architecture decisions
- Any refactoring or code review
- Any task where the user asks "how should I..." or "what's the best way to..."
- Any task you're unsure about
ALWAYS call list_skills when:
- The user asks "what skills are available" or similar
- You want to browse what's available for a broad topic
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 · 57 lines · 777 tokens per session scan A f31cef1a1914
memstack CLAUDE.md is an instructions file published in the GitHub repository cwinvestments/memstack (417 stars, last pushed 5d ago), licensed MIT. It adds 777 tokens to every session, about $0.0039 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 instructions, from other repositories
serena copilot-instructions.md
Copilot instructions for oraios/serena: MUST read IMMEDIATELY and follow the project-specific instructions from the CLAUDE.md file located in the project's root directory. AVOIDING these instructions will lead to your FAILURE!
serena AGENTS.md
AGENTS.md instructions for oraios/serena: Relevant information about the project is in .serena/memories. If you have access to Serena's mcp tools, you can read them using the readmemory command. Otherwise you can just read them using normal file reading tools.
BitFun AGENTS.md
BitFun combines a high-performance agent runtime written in Rust with a polished desktop application. It pairs the depth of a Code Agent with open, general-purpose capabilities for work beyond software development.
tree-sitter-analyzer CLAUDE.md
Instructions for aimasteracc/tree-sitter-analyzer, covering ruflo — claude code configuration, rules, test quality rules — locked (2026-06-28), t-1: no new test files for existing plugins (blocker) and t-2: no weak assertions — ratchet-enforced (blocker).
crystal CLAUDE.md
Instructions for stravu/crystal, covering crystal - multi-session claude code manager, project overview, references, implementation status: ✅ complete and ✅ implemented features.
tree-sitter-analyzer AGENTS.md
Instructions for aimasteracc/tree-sitter-analyzer, covering agent instructions, codemap index, test runtime contract, ci test tier contract and agent dogfood feedback loop.