agent-memory

A setup tool for giving coding agents shared project memory through a .memory directory and instruction files. It supports Claude Code, Codex, OpenCode, and Gemini CLI.

In plain words
What is it for?
Use it to create or repair agent-memory files in the current project. It can also avoid overwriting an existing memory directory unless replacement is explicitly requested.
Why use it?
It helps agents reuse project knowledge between sessions instead of repeatedly asking for the same setup command or context.

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/taichuy/agentmemory/agent-memory
Any agent
npx skills add taichuy/agentMemory --skill agent-memory
Clone the repo
git clone --depth 1 https://github.com/taichuy/agentMemory

Made for: Claude Code, Codex.

Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,097 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 $0.00071 $0.01097
Opus 5 $0.00036 $0.00549
Sonnet 5 $0.00014 $0.00219
Haiku 4.5 $0.00007 $0.00110

Measured 2d ago against content hash 38640c20ecd6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-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 2d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/install-memory.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.

skills/agent-memory/SKILL.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Memory

Initialize the current project with the taichuy/agentMemory memory template. The goal is to make project memory available to coding agents without asking the user to paste the remote install command.

Workflow

  1. Treat the current working directory as the target project unless the user gives another path.

  2. Do not overwrite an existing .memory/ directory unless the user explicitly asks for force/overwrite.

  3. Prefer the bundled installer from this skill directory. Use the known skill path if the tool exposes it; otherwise try the global paths created by the installer:

    python <skill-dir>/scripts/install-memory.py --dest .
    python "$HOME/.codex/skills/agent-memory/scripts/install-memory.py" --dest .
    python "$HOME/.claude/skills/agent-memory/scripts/install-memory.py" --dest .
    python "$HOME/.config/opencode/skills/agent-memory/scripts/install-memory.py" --dest .
    python "$HOME/.gemini/skills/agent-memory/scripts/install-memory.py" --dest .
    

    In Claude Code, ${CLAUDE_SKILL_DIR} may be used as <skill-dir>. If python is unavailable, try python3 or py. If the user asked to replace an existing .memory/, add --force.

  4. If the bundled script cannot run, manually copy assets/memory-template/.memory into the target project as .memory, then create or update these root files:

    • AGENTS.md
    • CLAUDE.md
    • GEMINI.md
  5. The root instruction files must contain this block, or an equivalent existing reference:

    # 记忆
    命中对应`记忆存储规则`自动更新对应记忆中
    @.memory/AGENTS.md
    
    ## 用户偏好
    @.memory/user-memory.md
    
  6. If a root instruction file already exists and already references .memory/AGENTS.md and .memory/user-memory.md, leave it unchanged.

  7. If a root instruction file exists but lacks the memory references, append the memory block instead of replacing the user's content.

  8. Finish by reporting whether .memory/ was installed, kept, or replaced, and which instruction files were created or updated.

  9. Before ending the turn, infer the user's primary communication language from the current conversation and project files. Ask in that language whether to initialize .memory/user-memory.md. Do not write user memory before the user confirms.

  10. If the user confirms, ask one compact initialization question group adapted to the project context. Include:

Read the full file on GitHub · 82 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 · 82 lines · 71 tokens per session scan A 38640c20ecd6

Subscribe to this mod's changes

agent-memory is a skill published in the GitHub repository taichuy/agentMemory (24 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 71 tokens to every session and 1,097 once invoked, about $0.0004 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

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 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-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