meerkat AGENTS.md

meerkat AGENTS.md is an instructions file for Codex, OpenCode from lukacf/meerkat. It costs 482 tokens per session, scanned A, original, Apache-2.0.

Developer instructions for Meerkat that make Make the main interface for building, checking, linting, testing, and end-to-end tests. Optional BuildBuddy support can run selected work through Bazel and remote build infrastructure.

In plain words
What is it for?
Running Rust builds, checks, lints, unit and integration tests, end-to-end tests, and BuildBuddy diagnostics when the required access and keys are available.
Why use it?
A single set of commands keeps local and optional remote build paths consistent. Diagnostic targets help identify problems with BuildBuddy configuration and test lanes.

Instructions file for CodexOpenCode

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/lukacf/meerkat/agents-md
Clone the repo
git clone --depth 1 https://github.com/lukacf/meerkat

Made for: Codex, OpenCode.

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 meerkat AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/lukacf/meerkat/agents-md.svg)](https://agentmods.dev/instructions/lukacf/meerkat/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/lukacf/meerkat/agents-md"><img src="https://agentmods.dev/badge/instructions/lukacf/meerkat/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 482 This file is loaded in full into every session.
When invoked 482 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.00482 $0.00482
Opus 5 $0.00241 $0.00241
Sonnet 5 $0.00096 $0.00096
Haiku 4.5 $0.00048 $0.00048

Measured 4d ago against content hash 5fbebba1d4ac, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

meerkat 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 4d 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.

AGENTS.md · 49 lines

What it actually says

AGENTS.md

This repository uses Make as the developer-facing command surface.

Cargo is the default backend:

make build
make check
make lint
make test
make agent-gate

BuildBuddy is opt-in. When the machine has BuildBuddy access, the same broad local lanes can run through the macOS arm64 Bazel/RBE path:

MEERKAT_BUILDBUDDY=1 make build
MEERKAT_BUILDBUDDY=1 make check
MEERKAT_BUILDBUDDY=1 make lint
MEERKAT_BUILDBUDDY=1 make test
MEERKAT_BUILDBUDDY=1 make e2e-fast
MEERKAT_BUILDBUDDY=1 make e2e-system
MEERKAT_BUILDBUDDY=1 make e2e-live
MEERKAT_BUILDBUDDY=1 make e2e-smoke

Explicit BuildBuddy targets are available when you do not want environment switching: make buildbuddy-build, make buildbuddy-check, make buildbuddy-clippy, make buildbuddy-test, make buildbuddy-test-unit, make buildbuddy-test-int, make buildbuddy-e2e-fast, and make buildbuddy-e2e-system. Live-provider lanes are available as make buildbuddy-e2e-live and make buildbuddy-e2e-smoke when provider keys are configured.

Run make buildbuddy-doctor when BuildBuddy setup looks suspicious. It checks the API key, pinned bb CLI, generated Bazel files, selector behavior, and lane isolation without printing secrets. Use BUILDBUDDY_DRY_RUN=1 with explicit BuildBuddy Make targets to inspect the selected command without running it.

For same-checkout multi-agent work, set a distinct RUST_LANE_ID per agent if you want stable warm local output roots. Separate Git worktrees are already isolated by path hash.

Avoid raw cargo and raw bb for normal repo work. Use ./scripts/repo-cargo for targeted Cargo commands and scripts/buildbuddy-dev only when extending or debugging the BuildBuddy local facade.

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. 4d ago First seen · 49 lines · 482 tokens per session scan A 5fbebba1d4ac

Subscribe to this mod's changes

meerkat AGENTS.md is an instructions file published in the GitHub repository lukacf/meerkat (20 stars, last pushed 4d ago), licensed Apache-2.0. It adds 482 tokens to every session, about $0.0024 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.