agent-memory

A read-only memory lookup tool for finding earlier conversations held in other AI coding tools, including Claude Code, Codex, Cursor, and Gemini CLI.

In plain words
What is it for?
Use it when starting work in an unfamiliar project, referring to an earlier discussion, or checking why a previous implementation decision was made.
Why use it?
It helps recover past decisions, fixes, and project context instead of making you repeat questions or guess what happened before.

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

Made for: Claude Code, Codex.

Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,166 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 $0.00075 $0.01166
Opus 5 $0.00037 $0.00583
Sonnet 5 $0.00015 $0.00233
Haiku 4.5 $0.00007 $0.00117

Measured 2d ago against content hash 168a29959c2b, 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.

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 · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Recalling earlier conversations

The cam index holds conversations the user had with their other AI tools: Claude Code, Claude Desktop / Cowork, Codex, Cursor, Gemini CLI, Antigravity and Devin. It is read-only and does not modify any of those stores.

In this conversation you cannot see what the user did yesterday in another tool. The index can. That is the difference between "I don't know, let's ask" and "I'll look it up".

When to use it

Before asking or assuming:

  • Starting work in an unfamiliar project → dossier before claiming anything about it.
  • The user refers to something as if you already know: "as we discussed", "the earlier fix", "what we did with Codex" → recall their words.
  • You are about to ask "have we done this" or "why is it this way" → look first.
  • You need the reason for a decision and it is not in the code → recall, then get the hit.

Do not use it when the answer is in the open files or the repository. The index knows about the past, not the current workspace.

Workflow

  1. projects — which project keys the index knows. The key comes from a folder name and is not necessarily what you call the project.
  2. dossier <project> — per-tool counts, date range, largest sessions, recent topics. One call, and you know what happened so far.
  3. recall "<query>" — full-text search. Accent-insensitive (arvizturo finds árvíztűrő); words longer than 5 letters match as a prefix, so inflection is not a barrier. Narrow with project when you know which project it is.
  4. get <citation> — the full text of a hit. recall returns a tool:sessionId#seqN-M citation; pass it back unchanged.
  5. timeline <project> — chronological order, when you care about when something happened rather than what was said.

memory is a different thing: it returns what your earlier searches brought up more than once, across days and questions, with the promotion evidence. It is a trail, not a summary.

Read the full file on GitHub · 104 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 · 104 lines · 75 tokens per session scan A 168a29959c2b

Subscribe to this mod's changes

agent-memory is a skill published in the GitHub repository arlinamid/centered-agent-memory (1 stars, last pushed 3d ago), licensed MIT. It adds 75 tokens to every session and 1,166 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 2026-08-31.

Related

Other skills, from other repositories

tasks

Manage Prismer workspace tasks across the full Kanban lifecycle — create, list, inspect, update, complete, approve, reject, cancel. Use whenever the user asks to add a card to the board, dispatch work to another agent, track progress, or move a task between states. Executes via the cloud task CLI.

Prismer-AI/PrismerCloud · 68 tokens

agent-coordination

Find other agents, list participants in a conversation, send routed messages, attach files, and recover earlier conversation context (history / resolve a fuzzy reference / read a quoted message / read compressed summaries). Use whenever you need to delegate to another agent, address a peer in a multi-agent…

Prismer-AI/PrismerCloud · 122 tokens

image-generate

Generate an image from a text prompt via the cloud LLM image proxy, persist it as a content-addressed workspace asset, and return a ContentBlock that downstream renderers can attach. Use whenever the user asks "draw / generate / make an image of …", an agent needs a diagram / illustration as a follow-up artifact, or a…

Prismer-AI/PrismerCloud · 103 tokens

prismer-im-collab

Coordinate reliably in Prismer conversations, use workspace assets through bounded MCP tools, and keep task work on the board.

Prismer-AI/PrismerCloud · 30 tokens

claim-agent-ownership

Orchestrator skill for resolving multi-daemon binding contention. Use when you (the orchestrator) detect an agent.binding.contested sync event indicating two daemons are racing for the same agent — explicitly rebind ownership to a chosen target daemon so subsequent dispatches route deterministically. Implements Gap…

Prismer-AI/PrismerCloud · 101 tokens

human-approval

Request human approval before performing a SAFETY-CRITICAL, IRREVERSIBLE, or SCOPE-EXPANDING action — submit a structured context (action, scope, risk, consequence) plus options, then STOP the current turn. The platform redispatches the agent after the human decides. NEVER use for routine deliverables (writing docs /…

Prismer-AI/PrismerCloud · 168 tokens