A command for recovering useful context from recent conversations, such as the last few exchanges, messages around a time, or messages matching a search term.

Use it with commands such as last5, around a time, or search followed by a keyword to retrieve conversation history for the current session or project.

It helps restore information when a conversation is long or earlier details are no longer visible in the current working context.

recall — Command for coding agents by bledden: A command for recovering useful context from recent conversations…

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/bledden/claude-recall-plugin/recall

Clone the repo

git clone --depth 1 https://github.com/bledden/claude-recall-plugin

Or install recall, the plugin that ships this one along with the rest of its 1 skill, 1 command, 4 hooks.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/bledden/claude-recall-plugin/recall.svg)](https://agentmods.dev/commands/bledden/claude-recall-plugin/recall)

Your own site

<a href="https://agentmods.dev/commands/bledden/claude-recall-plugin/recall"><img src="https://agentmods.dev/badge/commands/bledden/claude-recall-plugin/recall.svg" alt="Measured on agentmods" height="20"></a>

Per session 5 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,728 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.

Model	Per session	Once invoked
Fable 5	$0.00005	$0.01728
Opus 5	$0.00003	$0.00864
Sonnet 5	$0.00001	$0.00346
Haiku 4.5	$0.00001	$0.00173

Measured 4d ago against content hash fc072f25b75d, 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 4d 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 · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context Recall

The user wants to recover context from this conversation.

Step 1: Check for Quick Commands

FIRST, check if $ARGUMENTS contains a quick command and run it directly, then stop:

Session/project are auto-resolved. Current-session commands resolve the session from the native $CLAUDE_CODE_SESSION_ID (per-session, so concurrent sessions never cross), and current-project commands derive the project from the working directory — no $SESSION_ID/$SESSION_HASH plumbing needed. Commands that act on a specific session pass $CLAUDE_CODE_SESSION_ID explicitly.

lastN (e.g. last5, last10, last20 — any positive N) → python3 ${CLAUDE_PLUGIN_ROOT}/scripts/fetch_exchanges.py lastN
around <time> → python3 ${CLAUDE_PLUGIN_ROOT}/scripts/fetch_exchanges.py around <time>
search <keyword> → python3 ${CLAUDE_PLUGIN_ROOT}/scripts/fetch_exchanges.py search <keyword>
search <keyword> --all → python3 ${CLAUDE_PLUGIN_ROOT}/scripts/fetch_exchanges.py search <keyword> --all
search <keyword> --global → python3 ${CLAUDE_PLUGIN_ROOT}/scripts/fetch_exchanges.py search <keyword> --global
search <keyword> --project <name> → python3 ${CLAUDE_PLUGIN_ROOT}/scripts/fetch_exchanges.py search <keyword> --project <name>
search --tag <name> → python3 ${CLAUDE_PLUGIN_ROOT}/scripts/manage_tags.py search <name>
sessions → python3 ${CLAUDE_PLUGIN_ROOT}/scripts/manage_sessions.py list
sessions --all → python3 ${CLAUDE_PLUGIN_ROOT}/scripts/manage_sessions.py list --all
sessions --project <name> → python3 ${CLAUDE_PLUGIN_ROOT}/scripts/manage_sessions.py list --project <name>
session <id> <args> → python3 ${CLAUDE_PLUGIN_ROOT}/scripts/fetch_exchanges.py --session <id> <args>
tag <name> → python3 ${CLAUDE_PLUGIN_ROOT}/scripts/manage_tags.py add <name> $CLAUDE_CODE_SESSION_ID
tag <name> #<exchange> → python3 ${CLAUDE_PLUGIN_ROOT}/scripts/manage_tags.py add <name> $CLAUDE_CODE_SESSION_ID <exchange>
tags → python3 ${CLAUDE_PLUGIN_ROOT}/scripts/manage_tags.py list
stats → python3 ${CLAUDE_PLUGIN_ROOT}/scripts/manage_sessions.py stats
usage → python3 ${CLAUDE_PLUGIN_ROOT}/scripts/manage_sessions.py usage
prune --session <id> → python3 ${CLAUDE_PLUGIN_ROOT}/scripts/manage_sessions.py prune --session <id>
prune --before <date> → python3 ${CLAUDE_PLUGIN_ROOT}/scripts/manage_sessions.py prune --before <date>
export --session <id> → python3 ${CLAUDE_PLUGIN_ROOT}/scripts/manage_sessions.py export --session <id> (always emits JSON)
highlight "summary" → python3 ${CLAUDE_PLUGIN_ROOT}/scripts/highlight.py $CLAUDE_CODE_SESSION_ID "summary"
connect <session-id> "topic" → python3 ${CLAUDE_PLUGIN_ROOT}/scripts/manage_connections.py connect $CLAUDE_CODE_SESSION_ID <session-id> "topic"
connect --latest "topic" → python3 ${CLAUDE_PLUGIN_ROOT}/scripts/manage_connections.py connect-latest $CLAUDE_CODE_SESSION_ID "topic"
disconnect <session-id> → python3 ${CLAUDE_PLUGIN_ROOT}/scripts/manage_connections.py disconnect $CLAUDE_CODE_SESSION_ID <session-id>
inbox → python3 ${CLAUDE_PLUGIN_ROOT}/scripts/manage_connections.py inbox $CLAUDE_CODE_SESSION_ID
config <key> <value> → python3 ${CLAUDE_PLUGIN_ROOT}/scripts/manage_connections.py config $CLAUDE_CODE_SESSION_ID <key> <value>

Read the full file on GitHub · 116 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.

4d ago First seen · 116 lines · 5 tokens per session scan A fc072f25b75d

Subscribe to this mod's changes

recall is a command published in the GitHub repository bledden/claude-recall-plugin (23 stars, last pushed 1mo ago), licensed MIT. It adds 5 tokens to every session and 1,728 once invoked, about $0.0000 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.

Memory and context claude claude-code context plugin

recall

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Context Recall

Step 1: Check for Quick Commands

What this file has done since we first saw it

Other commands, from other repositories

diff

list

resume

save

remember

recall