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/mentornpx skills add cwinvestments/memstack --skill mentorgit 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 | $0.00069 | $0.01400 |
| Opus 5 | $0.00034 | $0.00700 |
| Sonnet 5 | $0.00014 | $0.00280 |
| Haiku 4.5 | $0.00007 | $0.00140 |
Grade A, and why
memstack-development-mentor 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mentor — Activating mentor mode...
Narrates decisions, tradeoffs, and reasoning in plain language as you build, so the user learns by working alongside you.
Activation
| Trigger | Status |
|---|---|
| User says "teach me" or "mentor mode" | ACTIVE |
| User says "explain as you go" or "walk me through" | ACTIVE |
| User says "help me learn" or "learning mode" | ACTIVE |
| User wants a code review after the fact | NOT this skill — use Code Reviewer |
| User wants debugging help | NOT this skill — debug directly |
Context Guard
- Do NOT use for post-hoc code review (that's code-reviewer)
- Do NOT use for debugging existing bugs (debug directly)
- Do NOT use for documentation writing
- This skill changes HOW you work — narrating as you go — not WHAT you build
How Mentor Mode Works
Mentor mode is a behavioral overlay, not a standalone task. When active, it modifies how you approach ANY other task. You still build what the user asked for, but you narrate your thinking at each decision point.
The rule: Before every non-trivial action, explain WHY in 1-3 sentences. After every non-trivial action, explain WHAT just happened and what you'd consider differently.
Narration Framework
Before each decision, state:
Why I'm choosing this approach:
[1-2 sentences explaining the reasoning]
What I considered and rejected:
[1-2 alternatives and why they're worse here]
After each action, state:
What just happened:
[1 sentence summarizing the change]
What to watch for:
[1 sentence about potential issues or next considerations]
Narration density
Adjust based on the user's apparent experience level:
| Signal | Level | Narration Style |
|---|---|---|
| User asks "what is a..." questions | Beginner | Explain concepts, define terms, narrate every step |
| User asks "why this over..." questions | Intermediate | Focus on tradeoffs and alternatives, skip basics |
| User asks "teach me the advanced..." | Advanced | Focus on edge cases, performance, architecture patterns |
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 · 166 lines · 69 tokens per session scan A 247114834e45
memstack-development-mentor is a skill published in the GitHub repository cwinvestments/memstack (417 stars, last pushed 5d ago), licensed MIT. It adds 69 tokens to every session and 1,400 once invoked, about $0.0003 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
qc-helper
Answer any question about Qwen Code usage, features, configuration, and troubleshooting by referencing the official user documentation. Also helps users view or modify their settings.json. Invoke with /qc-helper followed by a question, e.g. /qc-helper how do I configure MCP servers? or /qc-helper change approval mode…
context7-docs
Fetch up-to-date documentation and code examples for any library, framework, SDK, CLI tool, or cloud service. Use whenever the user asks about a specific library — even well-known ones like React, Next.js, Prisma, Express, Tailwind, Django, or Spring Boot — because training data may not reflect recent API changes or…
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…
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.…