remember

remember is a skill for Claude Code, Codex from mhmdreza-rafiei/agent-tools. It costs 105 tokens per session (855 once invoked), scanned A, original, MIT.

A session handoff system that saves important project progress and restores it later. It keeps the next coding session informed about what was done, what remains, and the current context.

In plain words
What is it for?
Use it at the end of a session to save progress and at the start of another to restore the recorded state.
Why use it?
It addresses the fact that a new AI session starts without the previous conversation and can otherwise repeat work or lose decisions.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

Good fit Use it at the end of a session to save progress and at the start of another to restore the recorded state.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mhmdreza-rafiei/agent-tools/remember
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.

Any agent
npx skills add mhmdreza-rafiei/agent-tools --skill remember
Clone the repo
git clone --depth 1 https://github.com/mhmdreza-rafiei/agent-tools

Made for: Claude Code, Codex.

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 remember

README.md
[![agentmods](https://agentmods.dev/badge/skills/mhmdreza-rafiei/agent-tools/remember/github.svg)](https://agentmods.dev/skills/mhmdreza-rafiei/agent-tools/remember)
Your own site
<a href="https://agentmods.dev/skills/mhmdreza-rafiei/agent-tools/remember"><img src="https://agentmods.dev/badge/skills/mhmdreza-rafiei/agent-tools/remember/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for remember

Your own site · 80×15
<a href="https://agentmods.dev/skills/mhmdreza-rafiei/agent-tools/remember"><img src="https://agentmods.dev/badge/skills/mhmdreza-rafiei/agent-tools/remember.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 105 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 855 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00105 $0.00855
Opus 5 $0.00053 $0.00428
Sonnet 5 $0.00021 $0.00171
Haiku 4.5 $0.00011 $0.00085

Measured 8d ago against content hash 028aa563c991, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

remember 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 8d 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/context/remember/SKILL.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI has no memory between sessions. Every new session starts blank. This skill fixes that. Save at the end, restore at the start — done consistently, nothing gets lost.

Memory lives in the context system: the canonical session state is context/memory/progress.md. /run-team owns team.md and /imprint owns ui-registry.md — read those on restore, never write them here.

Automation mode (default)

In automated/team flows, /remember save just saves — overwriting progress.md is its job, so don't prompt for the overwrite. The overwrite confirmation below is for interactive use. /remember restore still summarises what it restored (reality may have moved), but in automation it can proceed once summarised.

Security boundary

Never persist secrets. If a sensitive value appears (API keys, tokens, passwords, private keys, cookies, connection strings, webhook secrets, or any credential-like string), do not copy it to progress.md. Store a redacted placeholder (e.g. [REDACTED_API_KEY]). If unsure, treat it as sensitive and omit it. Run a final pass before writing to ensure nothing sensitive slipped in.

Invoke

/remember save (end of session) · /remember restore (start of session). Bare /remember → ask which, unless context makes it obvious.

Save

Capture only what a developer needs to continue cold — the essential state, not a transcript:

  • Current state — what works, what's partial, what's broken.
  • What was built — specific files/components/features this session (be precise).
  • Decisions made — choices future work depends on (and fold durable ones into architecture.md/plan.md).
  • Problems solved — so they aren't solved twice.
  • Next session starts with — the very next action, specific.
  • Open questions — anything unresolved.

Skip: implementation details visible in code, decisions already in the context files, and anything inferable from the codebase.

Write to context/memory/progress.md (if no context/, suggest /groundwork; else fall back to root memory.md). Interactive overwrite check (skipped in automation):

Read the full file on GitHub · 67 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. 8d ago First seen · 67 lines · 105 tokens per session scan A 028aa563c991

Subscribe to this mod's changes

remember is a skill published in the GitHub repository mhmdreza-rafiei/agent-tools (5 stars, last pushed 24d ago), licensed MIT. It adds 105 tokens to every session and 855 once invoked, about $0.0005 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 2026-09-03.

Related

Other skills, from other repositories

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens

establishing-project-context

Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.

GanyuanRan/Aegis · 45 tokens