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/zifeo/lade/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.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 | $0.00498 | $0.00498 |
| Opus 5 | $0.00249 | $0.00249 |
| Sonnet 5 | $0.00100 | $0.00100 |
| Haiku 4.5 | $0.00050 | $0.00050 |
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.
What it actually says
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
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
House rules
- All user-facing stderr goes through
message_box::MessageBox— nevereprintln!. The box is always emitted; only interactive parts (prompts, countdowns, sleeps) are gated onUiMode(QuietvsInteractive). See.cursor/rules/message-box.mdc. - Never rely on default values; be explicit. Prefer the simplest solution that compiles. Comment only non-obvious intent, not what the code does.
- Keep documented exit codes (
src/exit_codes.rs) stable across minor versions.lade status --jsonkeepsversion,global_config,hooks,project_config, andok; thehooksobject ispreexecpluspretool.
Project layout
src/— CLI crate. Key modules:pretool/(lade hookpreToolUse handler plus install into Cursor/Claude configs),audience.rs(detect()for Via, Audience, UI),prompt.rs(disclaimer flow),inject.rs/exec/(PTY execution + masking),status.rs,shell/(preexec integration),config/,message_box/.sdk/— the secret-loader crate (vault providers).tests/— Rust integration tests +installer_test.sh.scripts/,examples/tape/— shell-hook fixtures and README demo tapes.installer.sh,action.yml,Dockerfile,.github/workflows/— install & CI surface.
Maintainer note
The GitHub Action (action.yml) is not auto-published to the Marketplace:
on each release, tick "Publish this Action to the GitHub Marketplace" in the
release UI once.
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 · 49 lines · 498 tokens per session scan A fb13bc41aec3
lade AGENTS.md is an instructions file published in the GitHub repository zifeo/lade (127 stars, last pushed 13d ago), licensed MPL-2.0. It adds 498 tokens to every session, about $0.0025 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
claude-wrapper CLAUDE.md
Instructions for smartwatermelon/claude-wrapper, covering claude.md, what this is, commands, run tests and lint.
headson CLAUDE.md
Instructions for kantord/headson, covering headson — agents guide, mission, primary surfaces to mind, core pipeline (keep behaviors intact) and heuristics & semantics to preserve.
ralph CLAUDE.md
Instructions for SantanderAI/ralph, covering ralph — instrucciones del proyecto and paridad bash ↔ powershell (importante).
claude-code-statusline CLAUDE.md
Instructions for glauberlima/claude-code-statusline, covering claude.md, project overview, development commands, testing and run all tests (unit + integration).
auto-uv-env AGENTS.md
Instructions for ashwch/auto-uv-env, covering agents.md - the auto-uv-env story, what this repo is, architecture diagrams, runtime activation flow and repository lifecycle.
nightdev_rep AGENTS.md
Instructions for hiramgabriel1/nightdev_rep, covering agents.md, commands, architecture, key conventions and git workflow.