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.
npx agentmods add instructions/zippoxer/recall/claude-mdgit clone --depth 1 https://github.com/zippoxer/recallWrote 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.
[](https://agentmods.dev/instructions/zippoxer/recall/claude-md)<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>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 5.1 | $0.00659 | $0.00659 |
| Opus 5 | $0.00329 | $0.00329 |
| Sonnet 5 | $0.00132 | $0.00132 |
| Haiku 4.5 | $0.00066 | $0.00066 |
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 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 resumesrc/app.rs- Application state, search logic, background indexing threadsrc/ui.rs- Two-pane ratatui rendering, match highlightingsrc/tui.rs- Terminal setup/teardownsrc/theme.rs- Light/dark theme with auto-detectionsrc/session.rs- Core types: Session, Message, SearchResultsrc/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)
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.
- 6d ago First seen · 63 lines · 659 tokens per session scan C 76dcd7892e4c
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.
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.
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.
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.
CodexClaw AGENTS.md
Instructions for MackDing/CodexClaw, covering repository guidelines, repo structure, start and dev commands, test commands and lint and format.
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.
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).