Borrowing it
Nothing to install: this file belongs to samzong/Recall. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/samzong/Recall/main/AGENTS.mdgit clone --depth 1 https://github.com/samzong/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/samzong/recall/agents-md)<a href="https://agentmods.dev/instructions/samzong/recall/agents-md"><img src="https://agentmods.dev/badge/instructions/samzong/recall/agents-md/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.
<a href="https://agentmods.dev/instructions/samzong/recall/agents-md"><img src="https://agentmods.dev/badge/instructions/samzong/recall/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00959 | $0.00959 |
| Opus 5.5 | $0.00384 | $0.00384 |
| Sonnet 5.5 | $0.00192 | $0.00192 |
| Haiku 4.5 | $0.00096 | $0.00096 |
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 20d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Recall
Rust CLI/TUI for indexing and searching local AI coding sessions. Data flow: adapters -> sync -> SQLite -> search -> CLI/TUI.
Read the nested AGENTS.md before changing src/adapters/, src/db/,
src/tui/, extensions/, or website/.
CLAUDE.md links to this file; edit this file once.
Contributing
Repository owners, members, and collaborators are exempt. Everyone else,
including agents acting for a contributor, follows these rules;
.github/workflows/contribution-gate.yml checks them on every pull request.
- Work only on an open issue assigned to you. Check
assigneesingh issue view <issue>; to claim an unassigned issue, comment/assignand confirm you then appear inassignees. An assignment with no linked pull request after 15 days may be released. - Every pull request resolves an issue assigned to its author: put
Closes #<issue>in the description. - A human opens the pull request and authors every commit, signing off with
git commit -susing an email linked to their GitHub account. Bot or agent accounts must not open the pull request, author commits, or sign off. - The description has a
## Test evidencesection: the tool and version, OS, what you ran against real data or a real installation, the Recall output you observed, and what you could not verify. Tests andmake checkalone do not count. - When the check fails, fix the cause, then edit the description or push to run it again.
Build and verify
make checkis required before push and is the CI gate: dependency audit, format check, workspace Clippy with--all-targets --features bench, then workspace tests. Install the cargo-audit version pinned in.github/workflows/ci.yml.make buildbuilds core;cargo build -p recall-<name>builds an extension binary.cargo test <filter>runs focused core tests.- Core integration tests belong in
src/integration/, enabled bysrc/lib.rs;tests/fixtures/holds data. Do not add roottests/*.rstargets. Other workspace crates keep their own test layouts. - Website commands and checks are separate; see
website/AGENTS.md.
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.
- 20d ago Changed · +22 lines · +274 tokens per session 9c1306b20efa
- 27d ago Changed · -2 lines · -37 tokens per session fc1f5295dac0
- 1mo ago Changed · -75 lines · -1,141 tokens per session 6a46bb060cca
- 1mo ago Changed · +6 lines · +74 tokens per session 19df1947b982
- 1mo 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 (107 stars, last pushed 2d ago), licensed MIT. It adds 959 tokens to every session, about $0.0038 per session on Opus 5.5. 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.