v0.2 — recipe slate landed

Block AI coding agents on the same quality gates your humans hit.

klasp turns fmt, lint, type-check and test into hard agent boundaries. Drift, infinite loops, and broken PRs stop at the gate — not in human review.

$npx klasp@latest init View on GitHub →

Use case · overnight autonomy

Ship while you sleep. Wake up to PRs, not panic.

Autonomous agents need a deterministic done signal. Without one, an overnight run drifts: retry loops, exhausted context, force-pushed-broken commits. klasp is that signal — every iteration ends in a clean pass / fail with structured findings.

Without klasp overnight-run · pid 4471

23:42▸agent: implement checkout flow

00:15✗tests fail · agent guesses, retries with different approach

01:33✗lint errors · agent rewrites unrelated module

02:50✗stuck in test/lint loop · context window exhausted

04:12✗agent gives up → force-pushes broken code

07:00⨯main is red. 47 failed CI runs. 6h of compute burned.

With klasp overnight-run · pid 4472

23:42▸agent: implement checkout flow

23:58●klasp:format ✗ → 3 lines · agent fixes

00:14✓format · lint · agent advances

00:47●klasp:test ✗ → test_total::charges_tax · agent investigates

01:22✓all gates · commit · open PR #142

01:25▸agent: implement refund handler

07:00✓4 clean PRs in your queue. All green CI. Ready to review.

01 — deterministic done

Exit codes are unambiguous. Agents stop guessing whether they're finished — the gate said zero, the gate said one. No drift, no panic loops.

02 — structured findings

When a gate fails, klasp surfaces line-numbered diagnostics from cargo, pytest, your linter — so the agent fixes the actual error, not a hallucinated symptom.

03 — bounded context

Tight pass / fail loops mean each iteration burns a few hundred tokens, not tens of thousands. Overnight runs stay inside their context window.

Why klasp

One config. Same gates. Both audiences.

01 Stop bad PRs at the source

Agents can't merge what they can't pass. klasp wires your existing fmt / lint / test commands into deterministic exit-code gates the agent has to clear before it commits.

02 One config, both audiences

klasp.toml is the single source of truth. The same gate that guards your pre-commit hook guards the agent loop — no second config to drift out of sync.

03 Plug-in agent support

First-class for Claude Code and Codex CLI today. Managed CLAUDE.md / AGENTS.md blocks installed idempotently, with conflict detection and clean uninstall.

Recipes

Typed recipes for the gates you already run.

klasp.toml

# fmt — wraps an existing pre-commit hook
[[checks]]
name    = "format"
type    = "pre_commit"
hook_id = "rustfmt"

# lint — fallow groups multiple checks under one verdict
[[checks]]
name = "lint"
type = "fallow"

# test — pytest with JUnit-XML diagnostics surfaced to the agent
[[checks]]
name      = "test"
type      = "pytest"
junit_xml = true

# build — cargo with structured compiler diagnostics
[[checks]]
name       = "build"
type       = "cargo"
subcommand = "check"

Agents

First-class support for the agents you ship with.

Capability	Claude Code	Codex CLI
Pre-commit gate hooks	✓	✓
Managed config block	`CLAUDE.md`	`AGENTS.md`
Idempotent install / uninstall	✓	✓
Conflict detection	✓	✓
Cursor / Aider	— roadmap	— roadmap

Install

Pick your package manager.

npm / pnpm / bun

$ npx klasp@latest init

pipx (python)

$ pipx install klasp
$ klasp init

cargo (rust)

$ cargo install klasp
$ klasp init