cas-memory-management

A guide for saving and retrieving persistent project memories, such as conventions, preferences, bug fixes, and architectural decisions.

In plain words
What is it for?
Use it to record important project facts, search stored memories, and mark especially useful memories for future retrieval.
Why use it?
It prevents useful knowledge from being lost between sessions and makes previously learned context available later.

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/codingagentsystem/cas/cas-memory-management
Any agent
npx skills add codingagentsystem/cas --skill cas-memory-management
Clone the repo
git clone --depth 1 https://github.com/codingagentsystem/cas

Made for: Claude Code, Codex.

Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 218 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 $0.00050 $0.00218
Opus 5 $0.00025 $0.00109
Sonnet 5 $0.00010 $0.00044
Haiku 4.5 $0.00005 $0.00022

Measured 2d ago against content hash 5af3101c28cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cas-memory-management 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.

.claude/skills/cas-memory-management/SKILL.md · 24 lines

What it actually says

CAS Memory Management

Store memories proactively — don't wait to be asked.

When to Remember

  • After discovering project-specific patterns or conventions
  • After fixing non-trivial bugs (capture root cause + solution)
  • After learning how unfamiliar code works
  • When finding important architectural decisions
  • After resolving configuration or setup issues

Actions

  • Store: mcp__cas__memory action=remember title="..." content="..." entry_type=learning (types: learning, preference, context, observation)
  • Find: mcp__cas__search action=search query="..." doc_type=entry
  • Promote: mcp__cas__memory action=helpful id=<id> — increases priority for future retrieval
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. 2d ago First seen · 24 lines · 50 tokens per session scan A 5af3101c28cb

Subscribe to this mod's changes

cas-memory-management is a skill published in the GitHub repository codingagentsystem/cas (151 stars, last pushed 5mo ago), licensed MIT. It adds 50 tokens to every session and 218 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.