memory-maintain

A maintenance procedure for a memory database that stores project knowledge from past work. It finds duplicates, removes low-value records, and splits large entries into more focused ones.

In plain words
What is it for?
Use it to check memory health, merge duplicate technology-stack records, remove junk, and reorganize unfocused memories.
Why use it?
It keeps stored project information easier to search and less cluttered as the database grows. It is useful when search quality declines or after a plugin upgrade.

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/d2a8k3u/claude-code-memory/memory-maintain
Any agent
npx skills add d2a8k3u/claude-code-memory --skill memory-maintain
Clone the repo
git clone --depth 1 https://github.com/d2a8k3u/claude-code-memory

Made for: Claude Code, Codex.

Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,726 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 $0.00040 $0.01726
Opus 5 $0.00020 $0.00863
Sonnet 5 $0.00008 $0.00345
Haiku 4.5 $0.00004 $0.00173

Measured 2d ago against content hash aad83847e319, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

memory-maintain 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.

skills/memory-maintain/SKILL.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Memory Maintenance

Clean up noise, deduplicate records, and reorganize large memories. Run this after upgrading the plugin, when search quality degrades, or when memories have grown large and unfocused.

Steps

1. Assess

Run memory_health to get current counts, types, and staleness stats.

2. Deduplicate accumulative records

These records should exist at most once each. Search for duplicates and merge them.

Tech-stack:

  1. memory_search("Technology stack used", type="semantic")
  2. If multiple records have the tech-stack tag AND content starts with Technology stack used::
    • Collect all technology items from each record's comma-separated list
    • memory_update the most comprehensive record with the union of all items (sorted alphabetically)
    • memory_delete all other duplicates
  3. Tag collision check: If any record has the tech-stack tag but does NOT start with Technology stack used: (e.g., a detailed dependencies description from memory-init), rename its tag from tech-stack to tech-stack-detail via memory_update to prevent merge conflicts.

Active modules:

  1. memory_search("Active modules directories", type="semantic")
  2. If multiple records have the active-modules tag AND content starts with Active modules/directories::
    • Same approach: union all items, update the best, delete the rest
  3. Tag collision check: Same as above — rename non-accumulative records' tag to active-modules-detail.

3. Fix episodic titles

Episodic memories created before v1.2 often have no title, causing their content (starting with **Task:** or **Files modified:**) to be used as the label. This makes them indistinguishable in graphs and lists.

  1. memory_list(type="episodic", limit=100) — scan all episodic records
  2. For each record that has no title (title is null/empty):
    • If content starts with **Task:** — extract the task text after the marker, strip markdown bold, and use first ~80 chars as the title
    • If content starts with **Files modified:** — derive a title like "Session: N files in dir1, dir2"
    • If content contains both **Task:** and **Files modified:** lines — prefer the task text for the title
    • memory_update(id, { title: derivedTitle })
  3. Skip records that already have a meaningful title

Read the full file on GitHub · 131 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. 2d ago First seen · 131 lines · 40 tokens per session scan A aad83847e319

Subscribe to this mod's changes

memory-maintain is a skill published in the GitHub repository d2a8k3u/claude-code-memory (7 stars, last pushed 2mo ago), licensed MIT. It adds 40 tokens to every session and 1,726 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-assistant

Comprehensive memory management skill that guides memory capture and recall throughout sessions. Triggers when: user makes architectural decisions ("let's use", "we should", "decided to", "choosing"), discovers learnings ("TIL", "learned that", "discovered", "found out", "realized"), encounters blockers ("stuck on"…

zircote/git-notes-memory · 196 tokens

memory-recall

This skill should be used when the user asks about "past decisions", "previous learnings", "what did we decide", "how did we solve", "remember when", or mentions topics that may have stored memories. Also triggers when working on tasks where historical context would be valuable, such as "working on authentication"…

zircote/git-notes-memory · 83 tokens

opencli-sitemap-author

Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.

jackwener/OpenCLI · 67 tokens

golden-rss

Use when testing the rss golden build.

yusufkaraaslan/Skill_Seekers · 12 tokens

omh-code-review

This is a Hermes-native code-review workflow skill.

rlaope/oh-my-hermes · 46 tokens

redteam-web-detail-pack

Routing and boundary guidance for authorized general web application security testing. Use as a web testing router when the attack surface should be dispatched to more specific web vulnerability skills.

Netw0rkNoob/VulnClaw · 38 tokens