Borrowing it
Nothing to install: this file belongs to zifeo/lade. 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/zifeo/lade/main/AGENTS.mdgit clone --depth 1 https://github.com/zifeo/ladeWrote 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/zifeo/lade/agents-md)<a href="https://agentmods.dev/instructions/zifeo/lade/agents-md"><img src="https://agentmods.dev/badge/instructions/zifeo/lade/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/zifeo/lade/agents-md"><img src="https://agentmods.dev/badge/instructions/zifeo/lade/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 | $0.01604 | $0.01604 |
| Opus 5.5 | $0.00642 | $0.00642 |
| Sonnet 5.5 | $0.00321 | $0.00321 |
| Haiku 4.5 | $0.00160 | $0.00160 |
Grade A, and why
lade 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Conventions for AI agents contributing to lade (a Rust CLI). For using lade with coding agents and CI, see the README — this file is about working on the codebase itself.
Build & test
Stay in the Cursor sandbox for cargo / clippy / tests. Do not
request all because of sccache. enableSharedBuildCache remaps
Cargo dirs. It does not cover the sccache daemon. Seatbelt denies
AF_UNIX / 127.0.0.1, so .cargo/sccache-wrapper skips sccache when
CURSOR_SANDBOX is set. all is not a compile workaround.
Run these before proposing changes; they must all pass:
cargo build --workspace --locked
cargo test --workspace --locked
cargo clippy --all-targets -- -D warnings
shellcheck installer.sh
bash tests/installer_test.sh
Git hooks and the CI lint run through hk (hk.pkl; hk install once
per clone, hk check --all to check by hand). hk is a pinned tool in
lade.yml, installed by lade setup like every CLI the repo wraps.
PR titles follow the conventional regex in
.github/pr-title-checker-config.json, PR bodies the template in
.github/PULL_REQUEST_TEMPLATE.md: three blocks under two headings, a
motivation lead, What changed, and How to test with open boxes the
reviewer ticks. The user reviews the body before every push.
Tests share one mise cache, target/mise-cache (.cargo/config.toml).
The first run downloads the CLIs some tests pin (kubectl, vault); later
runs reuse them. CI persists it with actions/cache.
Tests never write to the developer's real Lade or mise state. Every
process a test spawns gets a temp HOME, or the matching LADE_* and
MISE_DATA_DIR dirs. env -i without HOME falls back to the real
one: the vault test did, rewrote ~/.local/share/mise/shims, and broke
every agent shell. docker-tests is a default feature, so a plain
cargo test runs it. CI fails a test job that touched $HOME
(scripts/home-canary.sh).
The age-plugin-lade post-quantum tests run age, age-keygen, and
age-plugin-pq from age 1.3.2 (pinned in lade.yml). Homebrew's age
has no age-plugin-pq.
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 Changed · +1 lines · +24 tokens per session 80df1e0c1efc
- 4d ago Changed · +9 lines · +126 tokens per session 1996713dab99
- 5d ago Changed · +12 lines · +173 tokens per session 8ef011f8c1b6
- 9d ago Changed · +4 lines · +59 tokens per session f5db78bfaec0
- 10d ago Changed · +10 lines · +178 tokens per session 55c7a74ec50d
- 15d ago Changed · +4 lines · +82 tokens per session 713d1b359a1a
- 18d ago Changed · +3 tokens per session ba83aa52f496
- 1mo ago Changed · +2 lines · +34 tokens per session 840287a87a6b
- 1mo ago Changed · +4 lines · +109 tokens per session 1613c20d7e73
- 1mo ago First seen · 63 lines · 816 tokens per session scan A ec5071671b5d
lade AGENTS.md is an instructions file published in the GitHub repository zifeo/lade (136 stars, last pushed today), licensed MPL-2.0. It adds 1,604 tokens to every session, about $0.0064 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).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.