memory-maintenance

memory-maintenance is a skill for Claude Code, Codex from jscott3201/aionforge-memory. It costs 48 tokens per session (368 once invoked), scanned A, original, Apache-2.0.

A maintenance workflow for Aionforge Memory, a system that stores durable facts and their history for later recall. It handles memory consolidation, audits, forgetting, and restoration.

In plain words
What is it for?
Use it to check the memory server, inspect consolidation status and provenance, consolidate derived memory when allowed, or forget and restore specifically identified records.
Why use it?
It helps explain where recalled information came from, find unfinished derived work, and manage stale or unwanted records without confusing memories with tasks.

Skill for Claude CodeCodex

Part of the aionforge-memory plugin — 7 skills, 3 commands, 1 hook shipped together

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/jscott3201/aionforge-memory/memory-maintenance
Any agent
npx skills add jscott3201/aionforge-memory --skill memory-maintenance
Clone the repo
git clone --depth 1 https://github.com/jscott3201/aionforge-memory

Made for: Claude Code, Codex.

Or install aionforge-memory, the plugin that ships this one along with the rest of its 7 skills, 3 commands, 1 hook.

Wrote 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.

agentmods badge for memory-maintenance

README.md
[![agentmods](https://agentmods.dev/badge/skills/jscott3201/aionforge-memory/memory-maintenance.svg)](https://agentmods.dev/skills/jscott3201/aionforge-memory/memory-maintenance)
Your own site
<a href="https://agentmods.dev/skills/jscott3201/aionforge-memory/memory-maintenance"><img src="https://agentmods.dev/badge/skills/jscott3201/aionforge-memory/memory-maintenance.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 368 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 $0.00048 $0.00368
Opus 5 $0.00024 $0.00184
Sonnet 5 $0.00010 $0.00074
Haiku 4.5 $0.00005 $0.00037

Measured 4d ago against content hash c8e85ecf7d8a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

memory-maintenance 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 4d 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.

plugins/aionforge-memory/skills/memory-maintenance/SKILL.md · 34 lines

What it actually says

Memory Maintenance

Requires an enabled Aionforge Memory MCP server.

Use this skill when the task is about the memory system itself.

Procedure

  1. Call server_status if connection state is unknown.
  2. Call consolidation_status to inspect backlog or failed derived work.
  3. Run consolidate only when the user/project policy permits mutating derived memory.
  4. Use audit_history to explain provenance, capture receipts, supersession hints, lifecycle changes, and rejection reasons.
  5. Use forget or unforget only when the user explicitly names the target memory id or asks for a specific lifecycle change.
  6. After lifecycle changes, search again when the user needs confirmation of visible recall state.

Scope

  • This skill maintains memory episodes and their derived work: consolidation, audit, decay, forget, and restore.
  • Work items are out of scope here. They are persistent and exempt from decay and forget; manage them with the work-tracking skill (work_advance to retire one to done/dropped), not forget. work_advance is itself audited, so audit_history still explains a work item's transitions.

Defaults

  • Preserve memory ids in answers.
  • Prefer audit evidence over guesses.
  • Treat ERR_NOT_FOUND as absent or unauthorized; do not infer hidden memory existence.
Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 4d ago First seen · 34 lines · 48 tokens per session scan A c8e85ecf7d8a

Subscribe to this mod's changes

memory-maintenance is a skill published in the GitHub repository jscott3201/aionforge-memory (10 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 48 tokens to every session and 368 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

brain-bitemporal

How to query the INITE Brain knowledge graph across time — the asOf parameter, validFrom/validUntil semantics, reading retracted facts, and the memorydiff "what changed between two cursors" surface. Use when the user's question has a temporal dimension ("on X date", "before Y", "what's new since last conversation").

inite-ai/inite-brain-service · 74 tokens

brain-recall

Recall everything brain knows about one specific entity — current profile, full bitemporal timeline, graph neighbours, and unresolved disagreements. Use when the user names a person/company/thing and asks "tell me about them", "what's their history", or "what do we still disagree about?". For a single-shot LLM…

inite-ai/inite-brain-service · 81 tokens

memory-review

Memory hygiene audit -- finds stale facts, contradictions, low-confidence entries, and consolidation candidates in Pensyve memory. Use periodically to maintain memory quality.

major7apps/pensyve · 33 tokens

session-memory

End-of-session memory capture -- classifies session signals using a tiered taxonomy and stores confirmed items via Pensyve. Use when ending a work session or when the user wants to capture what was learned.

major7apps/pensyve · 44 tokens

memory-informed-refactor

Pre-refactor context briefing -- loads relevant prior decisions, failures, and pitfalls from Pensyve memory before refactoring a module. Use before any refactor to avoid repeating past mistakes.

major7apps/pensyve · 42 tokens

memory-informed-debug

Debug with working memory -- before diagnosing, recall prior root causes and known-good diagnostic procedures; when a root cause is confirmed, capture it immediately. Use whenever debugging a non-trivial failure.

major7apps/pensyve · 42 tokens