New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Recall

by AgentSystemLabs in AgentSystemLabs/core

Save durable project knowledge to Mission Control's Recall (project memory) so future sessions start already knowing it.

MITAuto-check passedAgent Workflows

Install Recall

skills CLI
$ npx skills add AgentSystemLabs/core --skill recall -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install AgentSystemLabs/core recall --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/AgentSystemLabs/core.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/recall .claude/skills/recall && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
recall
GitHub stars
123
Token cost
~961 tokens
SKILL.md length
374 words
Files
1
Skills in repo
2
Repo updated
First seen
Licence
MIT

At a glance

Save durable project knowledge to Mission Control's Recall (project memory) so future sessions start already knowing it.

  • Decide something worth remembering about THIS project — an architecture fact
  • SKILL.md covers When to save a memory, How to save and Etiquette
  • Calls curl; needs MC_API_TOKEN
  • A decision and its rationale

What it does

Recall is an agent skill from AgentSystemLabs/core. Save durable project knowledge to Mission Control's Recall (project memory) so future sessions start already knowing it. Use when you discover or decide something worth remembering about THIS project — an architecture fact, a decision and its rationale, a convention, a stack detail, a glossary term, a known issue, or a useful discovery ("X lives in Y", "Z is generated"). Requires a Mission Control agent session (MCAPIURL, MCAPITOKEN, MCTASKID are injected automatically). Not for transient to-dos, run-specific…

Its SKILL.md is about 960 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Agent memory. The licence is MIT.

When your agent uses it

  • Decide something worth remembering about THIS project — an architecture fact
  • A decision and its rationale
  • A glossary term
  • A useful discovery (X lives in Y

Example prompts

  • “X lives in Y”
  • “Z is generated”
  • “/recall”

Requirements

  • A credential in MC_API_TOKEN

What it can do on your machine

Read from SKILL.md and the folder at commit 1174de2. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • curl

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use curl, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • MC_API_TOKEN

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Recall loads about 961 tokens when it runs. Until then it costs about 145 tokens; SKILL.md has 374 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~145
When it runs · the whole SKILL.md, loaded when a task matches
~961

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from AgentSystemLabs/core at commit 1174de2, republished under its MIT licence (© AgentSystemLabs). 374 words, ~961 tokens.

Download SKILL.mdSave it as .claude/skills/recall/SKILL.md (or your agent's skills folder).
name
recall
description
Save durable project knowledge to Mission Control's Recall (project memory) so future sessions start already knowing it. Use when you discover or decide something worth remembering about THIS project — an architecture fact, a decision and its rationale, a convention, a stack detail, a glossary term, a known issue, or a useful discovery ("X lives in Y", "Z is generated"). Requires a Mission Control agent session (MC_API_URL, MC_API_TOKEN, MC_TASK_ID are injected automatically). Not for transient to-dos, run-specific notes, or projects running outside Mission Control.
user-invocable
true

Mission Control agent sessions receive env vars automatically:

  • MC_API_URL — loopback API base (e.g. http://127.0.0.1:54321)
  • MC_API_TOKEN — bearer token for that API
  • MC_TASK_ID — the active task/session id

Mission Control maintains Recall, a curated, per-project memory that it assembles into a Session Brief and hands to every new session. When you learn something durable about this project, write it back so the next session doesn't rediscover it.

Skip this entirely when the MC env vars are missing (plain shell outside Mission Control).

When to save a memory

Save a memory when you establish a durable fact about the project — not about the current task:

  • decision — a choice that was made and why ("Use JWT instead of session cookies — stateless across the worker fleet")
  • architecture — where things live / how data flows ("Auth flow lives in useAuth")
  • convention — a project-specific pattern or do/don't ("All API errors go through handleDomainError")
  • stack — a language/framework/build/runtime/infra fact
  • glossary — a domain term and its meaning
  • known-issue — a current limitation, gotcha, or flaky area
  • discovery — a useful finding ("Migrations run on boot from ensureSchema")
  • overview / preference — what the project is / how the user likes to work here

Do not save: the task you were asked to do, TODOs, transient state, or anything only true for this one run. Prefer a few high-signal facts over many. Recall dedupes by title, so re-saving a known fact is harmless.

Show full SKILL.md (149 more words)Show less

How to save

First resolve the project id from the task, then POST the memory:

bash
# 1. Get the project id for this session.
PROJECT_ID=$(curl -s "$MC_API_URL/api/tasks/$MC_TASK_ID" \
  -H "authorization: Bearer $MC_API_TOKEN" \
  | sed -n 's/.*"projectId":"\([^"]*\)".*/\1/p')

# 2. Save a memory.
curl -s -X POST "$MC_API_URL/api/projects/$PROJECT_ID/memory" \
  -H "authorization: Bearer $MC_API_TOKEN" \
  -H "content-type: application/json" \
  -d '{
    "type": "decision",
    "title": "Use JWT instead of session cookies",
    "body": "Chosen for statelessness across the worker fleet.",
    "source": "agent",
    "confidence": "confirmed"
  }'
Fields
  • type (required) — one of overview, stack, architecture, decision, convention, glossary, known-issue, preference, discovery.
  • title (required) — a one-line headline. This is what gets injected into future briefs, so make it self-contained (≤ 200 chars).
  • body (optional) — a short detail: the why / where / how.
  • source — always send "agent" so the memory is tagged as agent-written.
  • confidence — "confirmed" when you verified it in the code, "inferred" when you're reasonably sure, "ambiguous" when unsure.
  • tags (optional) — a string array for filtering.

A 403 means the user has disabled agent memory writes in Settings → Recall — respect that and stop trying.

Etiquette

  • Save at most a handful of memories per session — the highest-signal facts only.
  • Keep each memory atomic (one fact per entry).
  • Don't echo the whole brief back; only write things that are genuinely new or now more certain.

© AgentSystemLabs, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/recall of AgentSystemLabs/core.

Open the folder on GitHubat commit 1174de2

Compare with similar skills

Recall next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Recall compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Recall this skillAgentSystemLabs/core123—~961Automated safety check: PassMIT
Coding Agent Session Findercode-yeongyu/oh-my-openagent70k1 repos~2.8kAutomated safety check: PassCustom licence
Claude-Mem Cloud Syncthedotmack/claude-mem98k1 repos~1kAutomated safety check: NotesApache-2.0
Cognee CLI Memory Commandstopoteretes/cognee32k1 repos~2.2kAutomated safety check: NotesApache-2.0
Neat-Freak Knowledge CloseoutKKKKhazix/khazix-skills21k—~1.9kAutomated safety check: PassMIT
Claude-Mem Searchthedotmack/claude-mem98k1 repos~511Automated safety check: PassApache-2.0

Similar skills

  • Coding Agent Session Finder

    code-yeongyu/oh-my-openagent

    Finds, reads and reconstructs past coding-agent sessions across Codex, Claude, OpenCode, Senpi and many other local agent logs.

    70k GitHub starsUsed in 1 repo~2.8k tokens
    Agent WorkflowsAuto-check passed

  • Claude-Mem Cloud Sync

    thedotmack/claude-mem

    Checks claude-mem cloud sync status and guides you through connecting a cmem.ai Pro account without the sync token ever passing through the chat.

    98k GitHub starsUsed in 1 repo~1k tokens
    Agent WorkflowsAuto-check: notes

  • Cognee CLI Memory Commands

    topoteretes/cognee

    Drives cognee from the terminal with remember, recall, forget and improve memory commands, dataset and config management and database migrations.

    32k GitHub starsUsed in 1 repo~2.2k tokens
    Agent WorkflowsAuto-check: notes

  • Neat-Freak Knowledge Closeout

    KKKKhazix/khazix-skills

    Brings project docs, agent rule files, authorized memory and leftover workspace files back in line with what the code and runtime actually do at the end of a work session.

    21k GitHub stars~1.9k tokensUpdated 7 days ago
    Agent WorkflowsAuto-check passed

  • Claude-Mem Search

    thedotmack/claude-mem

    Searches the user's persistent cross-session memory for timestamped observations synthesized from past agent sessions on cmem.ai.

    98k GitHub starsUsed in 1 repo~511 tokens
    Agent WorkflowsAuto-check passed

  • Beads Task Memory

    gastownhall/beads

    Tracks multi-session work with dependencies in the bd issue tracker so the agent can find ready tasks and recover its context after conversation compaction.

    28k GitHub stars~1.2k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from AgentSystemLabs/core

  • Ship

    AgentSystemLabs/core

    The single entry point for the AgentSystem engineering pipeline.

    123 GitHub stars~6.2k tokensUpdated 2 mo ago
    Auto-check: warnings

Categories

Questions about Recall

What does Recall do?

Save durable project knowledge to Mission Control's Recall (project memory) so future sessions start already knowing it. Recall is an agent skill from AgentSystemLabs/core. Save durable project knowledge to Mission Control's Recall (project memory) so future sessions start already knowing it.

When should I use Recall?

Recall fits situations like: decide something worth remembering about THIS project — an architecture fact; A decision and its rationale; A glossary term; A useful discovery (X lives in Y.

How do I install Recall in Claude Code?

Run `npx skills add AgentSystemLabs/core --skill recall -a claude-code`. Or copy the skill folder (.claude/skills/recall in AgentSystemLabs/core) into .claude/skills/recall in your project. Claude Code loads it when a task matches its description.

How do I install Recall in Codex?

Run `npx skills add AgentSystemLabs/core --skill recall -a codex`. Or copy the skill folder (.claude/skills/recall in AgentSystemLabs/core) into .agents/skills/recall in your project. Codex loads it when a task matches its description.

Can I use Recall in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add AgentSystemLabs/core --skill recall -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/recall, .gemini/skills/recall, .github/skills/recall and .opencode/skills/recall in your project.

What does Recall need to run?

Going by SKILL.md and its folder, Recall needs the command-line tools its instructions call (curl) and credentials named MC_API_TOKEN. Our summary lists: A credential in MC_API_TOKEN.

Does Recall access the network?

SKILL.md contains no URLs. Its commands use curl, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Recall safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Recall use?

Recall is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Recall use?

About 961 tokens (SKILL.md is roughly 3.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Recall?

Skills that share tags, products or a category with Recall: Coding Agent Session Finder (code-yeongyu/oh-my-openagent, 70k stars), Claude-Mem Cloud Sync (thedotmack/claude-mem, 98k stars), Cognee CLI Memory Commands (topoteretes/cognee, 32k stars) and Neat-Freak Knowledge Closeout (KKKKhazix/khazix-skills, 21k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Recall?

AgentSystemLabs (a GitHub organization) maintains it in AgentSystemLabs/core, which has 123 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on July 24, 2026.

Source: AgentSystemLabs/core on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.