review-memory

review-memory is a skill for Claude Code, Codex from stuartshields/claude-setup. It costs 35 tokens per session (1,383 once invoked), scanned A, original, MIT.

A review of the automatic project notes that an assistant has saved over time, including useful patterns and unwanted noise.

In plain words
What is it for?
Use it after a milestone, before new work, or when project memory becomes cluttered to inspect, keep, remove, or promote entries.
Why use it?
It helps prevent outdated or irrelevant notes from guiding future work. It also identifies patterns that should become permanent project instructions.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/stuartshields/claude-setup/review-memory
Any agent
npx skills add stuartshields/claude-setup --skill review-memory
Clone the repo
git clone --depth 1 https://github.com/stuartshields/claude-setup

Made for: Claude Code, Codex.

Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,383 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00035 $0.01383
Opus 5 $0.00017 $0.00691
Sonnet 5 $0.00007 $0.00277
Haiku 4.5 $0.00003 $0.00138

Measured 3d ago against content hash 795847b80419, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 3d 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.

skills/review-memory/SKILL.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: review-memory

When to Use

Run /review-memory when prompted by the memory review hook, or any time you want to audit what auto-memory has captured for this project. Use after completing a milestone, before starting new work, or when memory feels noisy.

Do NOT run this mid-task. Finish what you're working on first.

Mode Selection

  • Full mode (default): Reads all topic files, presents detailed categorisation table, acts on confirmation.
  • Compact mode (/review-memory --compact): Quick list of new memories with one-line summaries. Asks "promote, keep, or remove?" for each. No topic file reads. Use when context is low or time is short.

Full Mode

Step 1: Load Memory

Read MEMORY.md from the project's memory directory. The path follows this pattern: ~/.claude/projects/<project-path-encoded>/memory/MEMORY.md

Where <project-path-encoded> is the project root path with / replaced by -.

Also read any topic files referenced from MEMORY.md (e.g., feedback_testing.md, project_auth.md).

List what was found:

  • Total entries in MEMORY.md
  • Topic files and their one-line descriptions
  • Last modified dates

Step 2: Categorise Each Entry

For each memory entry, evaluate all three categories in this order:

  1. Remove? Is this stale, wrong, duplicated by CLAUDE.md/rules, or derivable from code/git? If yes → Remove.
  2. Promote? Does this encode a convention, decision, or constraint that should survive memory cleanup? If losing it would cause mistakes in future sessions, it belongs in CLAUDE.md, a rule file, or a skill → Promote.
  3. Keep only if the entry is still relevant but too situational or temporary for a permanent file (e.g., user preferences, in-flight research, external context not derivable from code).

Every "Keep" must include a one-line justification for why it doesn't belong in CLAUDE.md, a rule, or a skill. If you can't articulate why, it's probably a Promote.

Present the categorisation as a table:

Read the full file on GitHub · 141 lines

Changes

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.

  1. 3d ago First seen · 141 lines · 35 tokens per session scan A 795847b80419

Subscribe to this mod's changes

review-memory is a skill published in the GitHub repository stuartshields/claude-setup (2 stars, last pushed 3mo ago), licensed MIT. It adds 35 tokens to every session and 1,383 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.

Related

Other skills, from other repositories

memory

Claude Mind - Search and manage Claude's persistent memory stored in a single portable .mv2 file.

memvid/claude-brain · 21 tokens

bearing-diagnosis

Complete bearing fault diagnostic workflow using vibration analysis and the predictive-maintenance-mcp server. Use this skill when the user says "diagnose bearing", "bearing fault", "bearing check", "detect bearing damage", "bearing vibration analysis", "inner race fault", "outer race fault", "ball defect", "cage…

LGDiMaggio/predictive-maintenance-mcp · 93 tokens

prognostics

Prognostic assessment workflow: trend analysis, degradation onset detection, and Remaining Useful Life (RUL) estimation using the predictive-maintenance-mcp server. Use this skill when the user says "trend analysis", "degradation trend", "RUL", "remaining useful life", "prognosis", "prognostics", "failure prediction"…

LGDiMaggio/predictive-maintenance-mcp · 120 tokens

signal-management

Signal loading, generation, and cache management using the predictive-maintenance-mcp server. Use this skill when the user says "load signal", "import signal", "list signals", "available signals", "generate test signal", "create test data", "synthetic signal", "clear cache", "signal info", "what signals are loaded"…

LGDiMaggio/predictive-maintenance-mcp · 91 tokens

anomaly-detection

ML-based anomaly detection and model training for vibration signals using the predictive-maintenance-mcp server. Use this skill when the user says "anomaly detection", "train model", "detect anomalies", "outlier detection", "normal vs abnormal", "machine learning", "one-class SVM", "LOF", "local outlier factor"…

LGDiMaggio/predictive-maintenance-mcp · 100 tokens

gear-diagnosis

Gear fault diagnosis workflow using vibration analysis via the predictive-maintenance-mcp server. Use this skill when the user says "gear fault", "gear diagnosis", "gear mesh", "gearbox analysis", "gear vibration", "tooth damage", "gear defect", "diagnose gear", "gear mesh frequency", "sideband analysis", or wants to…

LGDiMaggio/predictive-maintenance-mcp · 78 tokens