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 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/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/huntsdesk/ve-kit/review-memory"><img src="https://agentmods.dev/badge/skills/huntsdesk/ve-kit/review-memory.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00058 | $0.01338 |
| Opus 5.5 | $0.00023 | $0.00535 |
| Sonnet 5.5 | $0.00012 | $0.00268 |
| Haiku 4.5 | $0.00006 | $0.00134 |
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 10d 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 — 159 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.
- 10d ago Changed · +1 lines 17b2186ec308
- 1mo ago Changed · +14 tokens per session 150bdea63582
- 1mo 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 (3 stars, last pushed 10d ago), licensed MIT. It adds 58 tokens to every session and 1,338 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
hive.context-preservation
Proactively extract critical values from tool results into working notes before automatic context pruning destroys them.
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.
memory-flush
Promote important recent log entries into MEMORY.md and prune stale ones.
Vizra ADK Memory System
Implement persistent memory, session context, and vector memory (RAG) for AI agents.
continuum-memory
Configure and use Continuum's two-tier memory system — mem0+Qdrant/Milvus for long-term facts, Redis for short-term sessions, with multi-tenant scopes (USER / AGENT / SHARED / RUN / CONVERSATION). Invoke when the user asks about "remember", "user preferences", "long-term memory", "vector search over memories"…
channel-canvas
How to work with a channel's standing project context — the "Archie" canvas a team pins in a channel — and with the channel's pinned-messages index. Load this when a channel has project context attached (presented to you as channel project context), when a pinned-messages index is in front of you or one of its lines…