recall CLAUDE.md

recall CLAUDE.md is an instructions file for Claude Code, Codex from zippoxer/recall. It costs 659 tokens per session, scanned C, original, MIT.

Repository instructions for recall, a terminal application that searches and resumes past conversations from several coding-agent tools. It describes the product’s design principles, Rust commands, and terminal user-interface testing workflow.

In plain words
What is it for?
Use them when building, testing, linting, or end-to-end testing recall, especially its search, indexing, and terminal interface.
Why use it?
They provide the project’s development rules and explain when the local search index must be cleared after parser changes.

Instructions file for Claude CodeCodex

Written for Codex and Claude Code: reads ~/.codex or $CODEX_HOME, but also the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

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 instructions/zippoxer/recall/claude-md
Clone the repo
git clone --depth 1 https://github.com/zippoxer/recall

Made for: Claude Code, Codex.

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 CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/zippoxer/recall/claude-md.svg)](https://agentmods.dev/instructions/zippoxer/recall/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/zippoxer/recall/claude-md"><img src="https://agentmods.dev/badge/instructions/zippoxer/recall/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 659 This file is loaded in full into every session.
When invoked 659 The same file — it is already loaded in full.
Security scan C 1 finding. 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 5.1 $0.00659 $0.00659
Opus 5 $0.00329 $0.00329
Sonnet 5 $0.00132 $0.00132
Haiku 4.5 $0.00066 $0.00066

Measured 6d ago against content hash 76dcd7892e4c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade C, and why

recall CLAUDE.md scanned grade C with 1 finding 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 6d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf ~/Library/Caches/recall # macOS
CLAUDE.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Purpose

Search and resume past conversations from Claude Code, Codex CLI, and Factory (Droid).

Principles

  • Delightful - Made with love, feels good to use
  • Simple, uncluttered, focused - Two panes, keyboard-driven, no chrome
  • Responsive - Instant startup via background indexing, sub-100ms search
  • Match-recency matters - Rank by most recent message containing the match (human memory anchors to recent context)
  • Seamless resume - Enter execs directly into the CLI, no intermediate steps

Development

cargo check          # Fast compile check (no binary)
cargo run            # Build debug + run
cargo test           # Run tests
cargo clippy         # Lint

To test the TUI end-to-end, use tmux:

# Clear index cache if testing parser changes
# macOS: ~/Library/Caches/recall, Linux: ~/.cache/recall
rm -rf ~/Library/Caches/recall        # macOS
rm -rf ~/.cache/recall                # Linux
cargo build && tmux new-session -d -s test './target/debug/recall'
tmux send-keys -t test 'search query'
tmux capture-pane -t test -p          # See output
tmux kill-session -t test             # Cleanup

Install

cargo install --path .

Architecture

Rust TUI for searching Claude Code, Codex CLI, and Factory conversation history.

  • src/main.rs - Entry point, event loop, exec into CLI on resume
  • src/app.rs - Application state, search logic, background indexing thread
  • src/ui.rs - Two-pane ratatui rendering, match highlighting
  • src/tui.rs - Terminal setup/teardown
  • src/theme.rs - Light/dark theme with auto-detection
  • src/session.rs - Core types: Session, Message, SearchResult
  • src/parser/ - JSONL parsers for Claude (~/.claude/projects/), Codex (~/.codex/sessions/), and Factory (~/.factory/sessions/)
  • src/index/ - Tantivy full-text search index, stored in ~/Library/Caches/recall/ (macOS) or ~/.cache/recall/ (Linux)

Key Patterns

  • Background indexing: spawns thread on startup, indexes most recent files first, sends progress via mpsc channel
  • Unicode-safe string handling: use char indices not byte indices when slicing (see highlight_matches, create_snippet)
  • Search ranking: combines BM25 relevance with recency boost (exponential decay, 7-day half-life)
  • Theme detection: queries terminal bg color via crossterm, falls back to COLORFGBG env var
  • Event handling: drains all pending events each frame to prevent mouse event flooding
  • Contextual status bar: hints adapt to state (e.g., scroll hint only when preview is scrollable)

Read the full file on GitHub · 63 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. 6d ago First seen · 63 lines · 659 tokens per session scan C 76dcd7892e4c

Subscribe to this mod's changes

recall CLAUDE.md is an instructions file published in the GitHub repository zippoxer/recall (199 stars, last pushed 7mo ago), licensed MIT. It adds 659 tokens to every session, about $0.0033 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

ai-code-interface.el AGENTS.md

AGENTS.md instructions for tninja/ai-code-interface.el, covering agents.md, common development commands, byte compilation, running tests and run a specific test file.

tninja/ai-code-interface.el · 2,539 tokens

ai-code-interface.el copilot-instructions.md

Copilot instructions for tninja/ai-code-interface.el, covering github copilot instructions for ai-code-interface.el, project overview, language and technology, code style and conventions and file naming.

tninja/ai-code-interface.el · 1,289 tokens

codex-usage-widget AGENTS.md

AGENTS.md instructions for ognjeeen/codex-usage-widget, covering agents.md, project, scope and decision discipline, authorization and repository safety and architecture boundaries.

ognjeeen/codex-usage-widget · 1,218 tokens

CodexClaw AGENTS.md

Instructions for MackDing/CodexClaw, covering repository guidelines, repo structure, start and dev commands, test commands and lint and format.

MackDing/CodexClaw · 649 tokens

codex-token-meter AGENTS.md

AGENTS.md instructions for prefect12/codex-token-meter, covering ai token meter development guide, project shape, build and verification, git workflow and ai token meter test loop.

prefect12/codex-token-meter · 1,357 tokens

codex-loop-orchestra AGENTS.md

Instructions for LEO001020/codex-loop-orchestra, covering loop discipline, 1. decomposition discipline (single-pass plan-and-solve), 3. return convention (all subagents, mandatory), 4. recoverable compression directive and 5. kernel trigger rules (ipybox, when enabled).

LEO001020/codex-loop-orchestra · 2,161 tokens