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/huntsdesk/ve-kit/review-memorynpx skills add HuntsDesk/ve-kit --skill review-memorygit clone --depth 1 https://github.com/HuntsDesk/ve-kitWrote 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/huntsdesk/ve-kit/review-memory)<a href="https://agentmods.dev/skills/huntsdesk/ve-kit/review-memory"><img src="https://agentmods.dev/badge/skills/huntsdesk/ve-kit/review-memory.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00044 | $0.01318 |
| Opus 5 | $0.00022 | $0.00659 |
| Sonnet 5 | $0.00009 | $0.00264 |
| Haiku 4.5 | $0.00004 | $0.00132 |
Grade A, and why
review-memory 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 5d 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Review Protocol
Reviews the auto-memory system that persists across Claude Code conversations. Scope for this project:
~/.claude/projects/<your-project-slug>/memory/
├── MEMORY.md (index, always loaded into context — lines after 200 are truncated)
└── *.md (individual memory files, loaded on demand)
Part of the review-* skill family. Cites ../_shared/review-checklist.md.
Owner: docs-manager agent.
When to invoke
- MEMORY.md approaching 200 lines (truncation risk)
- After multiple sessions create new memories without pruning
- Quarterly audit
- When memories start feeling stale or duplicated
Output contract
Board tasks only. Lean summary to main agent.
Step 1 — Inventory
- Read
~/.claude/projects/<your-project-slug>/memory/MEMORY.md— record line count, every- [Title](file.md) — hookentry - Glob every
*.mdin that directory (excludingMEMORY.md) - For each memory file, parse frontmatter:
name,description,type(user/feedback/project/reference) - Record body length and last-modified time
Step 2 — Index integrity
For MEMORY.md:
- Line count < 200 (lines after 200 are truncated out of context — critical)
- Every
*.mdmemory file referenced? (orphaned memory files are dead) - Every
- [link](file.md)resolves? - Every entry has a one-line hook < 150 chars?
- No duplicate entries?
- Organized semantically (not chronologically)?
Step 3 — Frontmatter validation
For each memory file:
| Issue | Severity |
|---|---|
| Missing frontmatter | high |
type missing or invalid (must be user/feedback/project/reference) |
high |
name missing |
medium |
description missing or generic |
medium |
| Body doesn't match declared type | high |
Type correctness
user— user role, preferences, responsibilities, knowledgefeedback— guidance given by user, with Why: + How to apply:project— ongoing work, goals, initiatives, with Why: + How to apply:reference— pointers to external systems
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.
- 5d ago First seen · 158 lines · 44 tokens per session scan A 7d5379f88e51
review-memory is a skill published in the GitHub repository HuntsDesk/ve-kit (2 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 1,318 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
memory
Search conversation history and understand Dream-managed profile and memory files.
context-fundamentals
This skill should be used when the user asks to "understand context", "explain context windows", "design agent architecture", "debug context issues", "optimize context usage", or discusses context components, attention mechanics, progressive disclosure, or context budgeting. Provides foundational understanding of…
knowledge-steward
AI工作经验知识库管理。适用于用户明确要求'保存到Obsidian'、'记录这个'、'save this insight'、'memo this'、'capture this'等知识沉淀场景。将对话中的提示词、模式、问题修复、想法和效率优化保存到Obsidian知识库,并自动同步到GitHub。.
digital-brain
This skill should be used when the user asks to "write a post", "check my voice", "look up contact", "prepare for meeting", "weekly review", "track goals", or mentions personal brand, content creation, network management, or voice consistency.
hive.note-taking
Maintain a free-form scratchpad of decisions, extracted values, and open questions so context pruning doesn't lose anything you still need.
hive.context-preservation
Proactively extract critical values from tool results into working notes before automatic context pruning destroys them.