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/morluto/leantoken/agents-mdgit clone --depth 1 https://github.com/morluto/leantokenWrote 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/morluto/leantoken/agents-md)<a href="https://agentmods.dev/instructions/morluto/leantoken/agents-md"><img src="https://agentmods.dev/badge/instructions/morluto/leantoken/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 | $0.00446 | $0.00446 |
| Opus 5 | $0.00223 | $0.00223 |
| Sonnet 5 | $0.00089 | $0.00089 |
| Haiku 4.5 | $0.00045 | $0.00045 |
Grade A, and why
leantoken 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository guidance
LeanToken is a Rust application and library providing token-bounded repository retrieval through CLI and MCP adapters.
Architecture
Servicesowns application behavior; CLI and MCP adapters remain thin.- Preserve deterministic ranking, exact token budgets, bounded memory, atomic SQLite generations, and request snapshot consistency.
- Document new scan, fan-out, storage, and concurrency bounds in
docs/architecture.md.
Development
Run focused tests while iterating. Before the first push, format the tree and
run the smallest relevant check or behavioral test that proves the change. Do
not block opening a pull request on the complete CI-equivalent suite.
Use cargo test-focused <module-or-test> to filter the library, binary, and
integration targets, and use the ownership map in docs/development.md when
choosing affected tests.
GitHub Actions owns normal Rust merge readiness and must pass:
cargo fmt --all -- --check
cargo clippy --all-targets --all-features -- -D warnings
cargo test-product
It also runs cargo test-extras for examples and benchmark behavior and checks
rustdoc for public APIs and documentation. Run a complete gate locally only
when reproducing CI, working without CI, or changing the gate itself. See
docs/development.md for the complete development, packaging, and release
workflow.
Change-specific validation
- For performance or scalability work, use
$optimize-accuracy-first. - For storage changes, include query-plan evidence and focused integration tests; a faster microbenchmark does not justify weaker atomicity, limits, freshness, or deterministic results.
- Treat MCP schema snapshots as protocol changes. Inspect the schema diff before
accepting an
instaupdate. - Prefer behavioral integration tests for observable contracts and unit tests for private invariants.
- Match surrounding Rust naming, documentation, and comment conventions.
Contributions
Use conventional commit prefixes and follow .github/pull_request_template.md.
For releases and npm publication, follow docs/development.md and
docs/releases.md; never replace an already-published version.
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 · 54 lines · 446 tokens per session scan A 4cb3f36be7b8
leantoken AGENTS.md is an instructions file published in the GitHub repository morluto/leantoken (23 stars, last pushed 3d ago), licensed Apache-2.0. It adds 446 tokens to every session, about $0.0022 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
mcpls copilot-instructions.md
Instructions for bug-ops/mcpls, covering copilot instructions for mcpls, type safety, idiomatic rust, architecture and async.
codesage AGENTS.md
Instructions for iliaal/codesage, covering codesage, build, sanity check before pushing, crate map and search pipeline.
mcpls rust-bridge.instructions.md
Instructions for bug-ops/mcpls, covering type safety, document state, diagnostics pipeline, concurrency and lock scope and file watcher.
mcpls mcp-tools.instructions.md
Instructions for bug-ops/mcpls, covering type safety, error handling and idiomatic dispatch.
mcpls rust-config.instructions.md
Instructions for bug-ops/mcpls, covering type safety and idiomatic config and msrv and dependencies.
aster AGENTS.md
Instructions for Zfinix/aster, covering aster, global rules, user-facing copy, rust conventions and module size.