memory_manager

A standard procedure for managing an agent’s layered memory: permanent instructions, compressed past context, and recent conversation. It describes how to inspect, search, and update those memory stores.

In plain words
What is it for?
Checking memory status, retrieving stored notes, distinguishing long-term facts from recent context, and recording information for future work.
Why use it?
It helps the agent recover relevant earlier information without treating every past message as equally important. It also reduces the risk of losing durable project instructions or user preferences.

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/aliasjeff/aclix/memory_manager
Any agent
npx skills add AliasJeff/ACLIx --skill memory_manager
Clone the repo
git clone --depth 1 https://github.com/AliasJeff/ACLIx

Made for: Claude Code, Codex.

Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 720 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 $0.00018 $0.00720
Opus 5 $0.00009 $0.00360
Sonnet 5 $0.00004 $0.00144
Haiku 4.5 $0.00002 $0.00072

Measured 2d ago against content hash b8278802c273, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

memory_manager 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/inspect.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

src/builtin-skills/memory_manager/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

Provide a reliable, repeatable procedure for an agent to inspect and update its Hierarchical Memory System:

  • Long-Term Memory (LTM): permanent user/project instructions and facts
  • Compressed Memory (CM): rolling historical summary inside the session
  • Short-Term Memory (STM): recent uncompressed messages inside the session

Standard Operating Procedure

Key facts (read first)

  • LTM is already injected into your System Prompt as <long_term_memory>...</long_term_memory>.
  • Treat <long_term_memory> as permanent instructions and facts. You MUST prioritize and adhere to it over ephemeral conversation text.
  • If LTM exceeds length thresholds, it is automatically chunked and ONLY the Top 3 BM25 retrieved fragments relevant to your current task are injected.

1) Inspect current STM/CM state (capacity/volume)

Use this when you need to answer questions like:

  • “How many messages are in STM right now?”
  • “Is Compressed Memory (historical summary) present?”
  • “Has rolling compression already happened?”

Procedure

  1. Read the injected anchor at the very top of the skill payload returned by read_skill. Extract the absolute path from:

    • [Skill Directory: <absolute_path>]
    • Call it INJECTED_SKILL_DIR (the directory that contains this skill’s SKILL.md).
  2. Invoke the python tool with:

    • scriptPath: INJECTED_SKILL_DIR + /scripts/inspect.py
    • args: one argument, the target cwd (string)
    • Do not use the shell for this inspection.
  3. Interpret the output:

    • The script prints a single JSON object, including:
      • cwd
      • messageCount
      • compressedMemoryPresent (CM)
      • shortTermMessageCount (STM)

2) Update / remember new Long-Term Memory (CRITICAL)

CRITICAL RULE: To UPDATE or REMEMBER new long-term information, you MUST edit the LTM markdown files directly using file_edit or file_write.

  • Global (user-level) LTM: ~/.aclix/ACLI.md
    • Use for: stable user preferences, writing style, tooling preferences, personal constraints, recurring workflows.
  • Project (cwd-level) LTM: ./ACLI.md
    • Use for: repo-specific rules, architecture constraints, domain facts, deployment instructions, team conventions.

Read the full file on GitHub · 75 lines

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. 2d ago First seen · 75 lines · 18 tokens per session scan A b8278802c273

Subscribe to this mod's changes

memory_manager is a skill published in the GitHub repository AliasJeff/ACLIx (23 stars, last pushed 4mo ago), licensed MIT. It adds 18 tokens to every session and 720 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens