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 skills add cwinvestments/memstack --skill grimoiregit clone --depth 1 https://github.com/cwinvestments/memstackWrote 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.
[](https://agentmods.dev/skills/cwinvestments/memstack/grimoire)<a href="https://agentmods.dev/skills/cwinvestments/memstack/grimoire"><img src="https://agentmods.dev/badge/skills/cwinvestments/memstack/grimoire/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.
<a href="https://agentmods.dev/skills/cwinvestments/memstack/grimoire"><img src="https://agentmods.dev/badge/skills/cwinvestments/memstack/grimoire.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 57 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00514 |
| Opus 5.5 | $0.00011 | $0.00206 |
| Sonnet 5.5 | $0.00006 | $0.00103 |
| Haiku 4.5 | $0.00003 | $0.00051 |
Grade A, and why
grimoire 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 1mo 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.
What it actually says
📖 Grimoire: Updating the Knowledge Library
Manage and update CLAUDE.md files across all projects.
Activation
When this skill activates, output:
📖 Grimoire: Updating the knowledge library.
Then execute the protocol below.
Protocol
- Identify the target project: use config.json to find the CLAUDE.md path
- Read the current CLAUDE.md if it exists
- Determine what to update based on the session's work:
- New API endpoints built
- New database tables/migrations
- New pages or components added
- Architecture decisions made
- Environment variables added
- Dependencies installed
- Update the CLAUDE.md:
- Keep existing content intact
- Add new entries under the right headings
- Don't duplicate existing entries
- Use consistent formatting
- If no CLAUDE.md exists: create one with standard sections:
- Project Overview, Tech Stack, Directory Structure, Key Files
- API Endpoints, Database Schema, Environment Variables, Dev Commands
Inputs
- Project name (maps to config.json entry)
- What was built/changed this session
Outputs
- Updated CLAUDE.md file
- Summary of what was added
Example Usage
User: "update claude.md with the CC Monitor stuff"
📖 Grimoire: Updating the knowledge library.
Reading: C:\Projects\AdminStack\CLAUDE.md
Adding to API Endpoints:
- POST/GET/PATCH/DELETE /api/cc-sessions
- POST /api/cc-sessions/report
Adding to Database Schema:
- cc_sessions (020_cc_sessions.sql)
Adding to Environment Variables:
- CC_MONITOR_API_KEY
CLAUDE.md updated ✓
Level History
- Lv.1: Base: CLAUDE.md read/write with section management. (Origin: MemStack v1.0, Feb 2026)
- Lv.2: Enhanced: Added YAML frontmatter, activation message, auto-detect what changed. (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.
- 1mo ago Changed 06035a528b4d
- 1mo ago First seen · 73 lines · 28 tokens per session scan A 699c7004640c
grimoire is a skill published in the GitHub repository cwinvestments/memstack (425 stars, last pushed 4d ago), licensed MIT. It adds 28 tokens to every session and 514 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.
Other skills, from other repositories
catchup
Restore context after /clear by summarizing recent work and project state.
atomic-wiki
Conversational wiki and capture-bucket routing. Fires when the user wants a place, space, or folder for notes, research, tickets, raw dumps, or knowledge capture — checks the block in /.claude/CLAUDE.md; if the cwd is under a registered realm, creates the folder as a bucket via atomic wiki bucket add rather than a…
memory-factcheck
A check that compares the project’s saved agent notes with the current code, database, issue tracker, and files. It identifies notes whose claims are outdated or no longer match reality.
fable-context-thrift
Use at the start of any multi-step task and during exploration — before reading files, searching, or re-checking completed work, especially when tempted to read whole files, re-verify known facts, or run independent lookups one at a time.
context-mode
Use context-mode tools (ctxexecute, ctxexecutefile) instead of Bash/cat when processing large outputs. Triggers: "analyze logs", "summarize output", "process data", "parse JSON", "filter results", "extract errors", "check build output", "analyze dependencies", "process API response", "large file analysis", "page…
deep-clean
Full-spectrum consolidation of AI agent configuration files. Goes beyond memory-only dream skills: audits and optimizes context files (AGENTS.md/AGENTS.md/GEMINI.md/.cursorrules), rules, skills, and memory. Detects stale references, dead file paths, duplicated rules, stack mismatches, contradictions, vague directives…