recall

A command for searching past Claude Code, Codex, and Cursor sessions about a topic and producing a brief of the relevant decisions and current state.

In plain words
What is it for?
Use it to recall a previous task, compare tried and rejected approaches, or locate source, session, and identifier references.
Why use it?
It helps recover context from earlier agent sessions instead of repeating research or reconstructing decisions from memory.

Command

Part of the session-recall plugin — 2 skills, 2 commands, 1 agent, 3 hooks shipped together

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 commands/absolutemode/session-recall/recall
Clone the repo
git clone --depth 1 https://github.com/AbsoluteMode/session-recall

Or install session-recall, the plugin that ships this one along with the rest of its 2 skills, 2 commands, 1 agent, 3 hooks.

Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 182 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 $0.00021 $0.00182
Opus 5 $0.00010 $0.00091
Sonnet 5 $0.00004 $0.00036
Haiku 4.5 $0.00002 $0.00018

Measured 3d ago against content hash faccebc571d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 3d 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.

commands/recall.md · 16 lines

What it actually says

Recall the topic: "$ARGUMENTS" from the unified Claude Code + Codex + Cursor session index.

If the host exposes the dedicated recall subagent, dispatch it (in Claude Code: subagent_type: session-recall:recall). Otherwise search iteratively with recent_sessions, recall_search, expand_around/step, and grep.

Use a requested claude, codex, or cursor source filter; otherwise search all three. Return only a tight brief: task, key decisions and why, tried/rejected approaches, current state, and source + session_id + uuid pointers.

If "$ARGUMENTS" is empty, ask the user what to recall.

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. 3d ago First seen · 16 lines · 21 tokens per session scan A faccebc571d9

Subscribe to this mod's changes

recall is a command published in the GitHub repository AbsoluteMode/session-recall (12 stars, last pushed 26d ago), licensed MIT. It adds 21 tokens to every session and 182 once invoked, about $0.0001 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.