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/samzong/recall/agents-mdgit clone --depth 1 https://github.com/samzong/RecallWhat 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 | $0.01789 | $0.01789 |
| Opus 5 | $0.00894 | $0.00894 |
| Sonnet 5 | $0.00358 | $0.00358 |
| Haiku 4.5 | $0.00179 | $0.00179 |
Grade A, and why
Recall AGENTS.md 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.
How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to AI coding agents (Claude Code, Codex, OpenCode,
etc.) when working with code in this repository. Module-level rules live in
nested AGENTS.md files: crates/rx/, src/adapters/, src/db/, src/tui/,
extensions/, and website/ — read the one for the directory you are
changing. Provider admission is in crates/rx/PROVIDERS.md.
Overview
Recall is a Rust CLI/TUI application that indexes AI coding sessions from local
tools (Claude Code, Codex, OpenCode, Cursor, ...) into one SQLite database for
full-text/semantic search, usage tracking, JSONL export/import, session
sharing, and resume. The repo is a Cargo workspace: the core application crate
at the root, the independent rx launcher under crates/rx, plus official
extension crates under extensions/. Nothing is
published to crates.io — these are application binaries, not library crates.
Commands
make check # full gate: audit → fmt --check → clippy -D warnings → test
make build # debug build
make run # launch TUI
make sync # cargo run -- sync (FORCE=1 reprocesses all)
make search Q="query" # CLI search
make bench # CodSpeed benchmarks (needs the codspeed CLI)
cargo test <name> # run a single test by name filter
cargo test integration::regression # regression suite
cargo test integration::eval_harness # eval harness
make check must pass before push. CI runs exactly the same command — there is
no CI-only logic. The gate uses --workspace and --features bench, so it
covers extension crates, crates/rx, and the bench_api shim that benches/ compiles
against. Build a single extension with cargo build -p recall-<name>. Build the
launcher with cargo build -p rx.
Core releases use cargo-release: make release-patch is a dry run; add
EXECUTE=1 to bump, commit, tag, and push. The bump is chosen by whoever cuts
the release, not derived from the commit types. A pre-release hook prepends the
changelog entry for that version with git-cliff, so CHANGELOG.md is part of
the release commit and of the tag it describes, and the GitHub release notes
are read back out of it. Existing changelog content is never rewritten, so
hand-written upgrade notes survive. The v* tag triggers the binary build.
Extensions release independently: bumping an extension's package version in a
PR is the release intent — after merge, a workflow creates the
recall-<name>-v<version> tag, builds binaries, and regenerates the catalog.
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.
- 3d ago First seen · 125 lines · 1,789 tokens per session scan A 2822801a1a61
Recall AGENTS.md is an instructions file published in the GitHub repository samzong/Recall (76 stars, last pushed 3d ago), licensed MIT. It adds 1,789 tokens to every session, about $0.0089 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.
Other instructions, from other repositories
Binder AGENTS.md
Instructions for mpazik/Binder, covering binder, tech stack, monorepo structure, testing and development.
cowork-z CLAUDE.md
Instructions for kevinlin/cowork-z, covering claude.md, project overview, commands, architecture and multi-process overview.
chatmux CLAUDE.md
Claude Code instructions for echoedinvoker/chatmux, covering chatmux, commands, directory structure, architecture and pattern selection.
siyuan AGENTS.md
AGENTS.md instructions for siyuan-note/siyuan, covering agents.md, 1. non-negotiable constraints, do not hand-edit, verification and prohibited operations and 2. project-specific rules.
skills AGENTS.md
Instructions for qdrant/skills, covering qdrant skills, project overview, project structure, navigating skills locally and conventions.
awesome-copilot-id AGENTS.md
Instructions for GulajavaMinistudio/awesome-copilot-id, covering communication, explanation and documentation, markdown formatting, user communication style and workflow & methodology.