memory-recall

A workflow for loading and summarising stored project memory at the start of a session or when asked about earlier work. It supports Claude.ai and Claude Code, which are environments for using Claude as a coding assistant.

In plain words
What is it for?
Use it to answer questions such as what the agent remembers, where work stopped, and what should happen next.
Why use it?
It helps an agent recover the current project state and pending work instead of starting without 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/shandar/memory-map/memory-recall
Any agent
npx skills add shandar/memory-map --skill memory-recall
Clone the repo
git clone --depth 1 https://github.com/shandar/memory-map

Made for: Claude Code, Codex.

Per session 156 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 843 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 $0.00156 $0.00843
Opus 5 $0.00078 $0.00421
Sonnet 5 $0.00031 $0.00169
Haiku 4.5 $0.00016 $0.00084

Measured 2d ago against content hash 3744749b334c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

memory-recall 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/memory-recall/SKILL.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Memory Recall

Load and intelligently summarise stored memory so a session can pick up exactly where the last one ended.

Works in claude.ai (reads via memory_user_edits view) and Claude Code (reads ~/.claude/memory.md). Detected automatically.


Step 0 — Detect environment

Signal Environment Load
memory_user_edits tool is available claude.ai references/claude-ai.md
Not available / running in terminal Claude Code references/claude-code.md

Read the relevant reference file before proceeding.


Core Protocol

Step 1 — Read the full memory store

Use the environment-appropriate read command (see references) to fetch all stored entries.

Step 2 — Sort entries by relevance to the current request

Memory entries fall into priority tiers:

Tier 1 — Always surface:

  • CURRENT STATE SNAPSHOT (what's live, what's imminent)
  • Anything tagged "PENDING" or "next" in entries

Tier 2 — Surface if the user asked for context:

  • Project deliverables, decisions, frameworks
  • Recent event details, dates, links

Tier 3 — Surface only if directly relevant to the immediate query:

  • Historical context, completed work, design tokens
  • Personal/operating preferences (PWP, communication style)

Step 3 — Present the recall

Match the format to the trigger:

Proactive recall (start of session, no specific question):

Picking up where we left off:

Current state — [from CURRENT STATE SNAPSHOT entry, paraphrased]

Pending items:
→ [item 1]
→ [item 2]
→ [item 3]

Active projects: [list]

Say "show me the full memory map" to see everything stored.

On-demand recall ("what do you remember?"):

Memory map — [N] entries stored

CURRENT STATE
[paraphrase]

PROJECTS
→ [project 1]: [one-line status]
→ [project 2]: [one-line status]

DELIVERABLES
[count] documents, [count] emails, [count] events

PREFERENCES
[note operating style, tools, communication preferences]

Specific recall ("what do you remember about X?"):

Read the full file on GitHub · 119 lines

Files

What ships with it

2 files 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 · 119 lines · 156 tokens per session scan A 3744749b334c

Subscribe to this mod's changes

memory-recall is a skill published in the GitHub repository shandar/memory-map (2 stars, last pushed 4mo ago), licensed MIT. It adds 156 tokens to every session and 843 once invoked, about $0.0008 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

join-meeting

AgentCall (agentcall.dev) — Join a video meeting (Google Meet, Teams, Zoom) as an AI bot with voice and visual presence. Supports audio-only mode with voice intelligence (barge-in, interruptions), text-to-speech mode, and webpage modes for custom UI. Use when asked to join a call, attend a meeting, or participate in a…

pattern-ai-labs/agentcall · 80 tokens

hwp

Use this skill whenever the user wants to read, create, or edit Korean Hangul Word Processor documents (.hwp or .hwpx files). Triggers include any mention of 'hwp', 'hwpx', '한글 문서', '아래한글', '한컴오피스', or uploading/attaching .hwp/.hwpx files. Also use when extracting text from Korean reports or producing Korean-formatted…

DoHyun468/claw-hwp · 248 tokens

quiz-me

Quiz the user on root cause and intended fix BEFORE writing any non-trivial code, then verify comprehension of every change after. Use when the user asks for a bug fix, refactor, or feature and wants to stay technically sharp instead of vibe-coding. Also use when the user says "quiz me", "don't let me vibe code", or…

emanzurv/quiz-me-skill · 82 tokens

website-deploy-builder

Plan what to build on Website Deploy (simple-host.app). Helps a user decide whether their idea fits the static + light-backend model, maps it to concrete patterns (shared JSON state with atomic ops, append-only collections, private/password-locked pages on a custom domain, drop-in comments/feedback widgets…

vineetu/simple-host · 114 tokens

connect-domain

Connect a user's own custom domain (subdomain e.g. recipes.brand.com via CNAME, or apex e.g. brand.com via A record) to a site already deployed on simple-host. Use when a user wants their site served from their own domain with automatic HTTPS, or wants a private/password-protected site (privacy is offered only on a…

vineetu/simple-host · 108 tokens

name-cop

A naming process, not a name generator. Applies the SMILE and SCRATCH frameworks created by Alexandra Watkins in her book Hello, My Name Is Awesome. Builds a brand brief, generates candidates across several angles, kills any that trips a SCRATCH deal breaker, and scores the survivors on SMILE. Use when naming a…

jainulabudeenm/name-cop · 98 tokens