recall

recall is a command for Claude Code from avelikiy/great_cto. It costs 27 tokens per session (1,051 once invoked), scanned A, original, MIT.

A project-knowledge search command that looks through session history and written documents for information about a concept.

In plain words
What is it for?
Use it to search for topics such as authentication, quotas, or dependencies across logs and the docs tree.
Why use it?
It helps recover decisions and past events when the relevant information may be in either a session log or project documentation.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the great-cto plugin — 40 skills, 44 commands, 70 agents shipped together

Good fit Use it to search for topics such as authentication, quotas, or dependencies across logs and the docs tree.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add avelikiy/great_cto
Claude Code
/plugin install great-cto

Made for: Claude Code.

Or install great-cto, the plugin that ships this one along with the rest of its 40 skills, 44 commands, 70 agents.

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 recall

README.md
[![agentmods](https://agentmods.dev/badge/commands/avelikiy/great_cto/recall/github.svg)](https://agentmods.dev/commands/avelikiy/great_cto/recall)
Your own site
<a href="https://agentmods.dev/commands/avelikiy/great_cto/recall"><img src="https://agentmods.dev/badge/commands/avelikiy/great_cto/recall/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 recall

Your own site · 80×15
<a href="https://agentmods.dev/commands/avelikiy/great_cto/recall"><img src="https://agentmods.dev/badge/commands/avelikiy/great_cto/recall.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,051 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 $0.00027 $0.01051
Opus 5 $0.00014 $0.00526
Sonnet 5 $0.00005 $0.00210
Haiku 4.5 $0.00003 $0.00105

Measured yesterday against content hash 222517c0a276, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 yesterday.

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 · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the great_cto /recall command. Answer "what does this project already know about $ARGUMENTS?" from two places: what HAPPENED (session logs) and what is WRITTEN DOWN (the docs/ tree). A concept the operator half-remembers is as likely to live in an ADR as in a session.

Step 1 — Search session logs

QUERY="${ARGUMENTS:-}"
LOG_DIR=".great_cto/logs"

if [ -z "$QUERY" ]; then
  echo "Usage: /recall <keyword>"
  echo "Examples: /recall jwt  |  /recall quota  |  /recall board  |  /recall npm"
  exit 0
fi

# Search 1: match in concepts frontmatter field (highest precision)
echo "=== Concept matches ==="
grep -ril "concepts:.*${QUERY}" "$LOG_DIR"/session-*.md 2>/dev/null | sort -r | head -10

# Search 2: match in full log body (broader)
echo "=== Body matches ==="
grep -ril "${QUERY}" "$LOG_DIR"/session-*.md 2>/dev/null | sort -r | head -10

Step 1b — Search the documentation

Sessions say what happened; docs/ says what was decided and why. Ranked, not grepped — an exact-substring match over a hundred and sixty documents returns either nothing or everything, and neither is an answer.

Zero dependencies: the BM25 index is built in memory per call and runs in about a tenth of a second over this repository's corpus.

QUERY="${ARGUMENTS:-}"
MS="${CLAUDE_PLUGIN_ROOT:-$(ls -d "$HOME"/.claude/plugins/cache/*/great_cto/*/ 2>/dev/null | sort -V | tail -1 | sed 's|/$||')}"
MS="$(ls -d $MS/*/ 2>/dev/null | sort -V | tail -1 | sed 's|/$||')/scripts/lib/memory-search.mjs"
[ -f "$MS" ] || MS="scripts/lib/memory-search.mjs"

if [ -n "$QUERY" ] && command -v node >/dev/null 2>&1 && [ -f "$MS" ]; then
  echo "=== Documents ==="
  # Prints one of three things, and they are different answers: ranked hits,
  # "no matches in N documents" (the corpus was read and holds nothing), or
  # "nothing to search" (this project has no docs/ at all).
  node "$MS" "$QUERY" --source docs --limit 6
fi

Step 2 — Display results

For each unique matching file (deduplicate concept + body matches), show:

  • Filename (date + slug)
  • concepts: frontmatter field (if present)
  • ## Done section bullets (first 5)
  • ## Decisions section (first 3 bullets)

Read the full file on GitHub · 99 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. yesterday Changed 222517c0a276
  2. 5d ago First seen · 99 lines · 27 tokens per session scan A f1e033ea04be

Subscribe to this mod's changes

recall is a command published in the GitHub repository avelikiy/great_cto (89 stars, last pushed today), licensed MIT. It adds 27 tokens to every session and 1,051 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 2026-09-03.