Clear-Sights/Makoto

16 stars · Last commit 2026-06-19

When Claude says “tests pass”, makoto checks the record — every claim held against the agent's own logged deeds; fakes blocked, not warned. Each check ships at measured zero false positives. 誠

README preview

# Makoto

[![CI](https://github.com/skill-labV2/Makoto/actions/workflows/ci.yml/badge.svg)](https://github.com/skill-labV2/Makoto/actions/workflows/ci.yml)

**An integrity hook for Claude Code that watches the agent's _own_ tool calls and blocks the ones
that fake a check.** When Claude says it did something — ran the tests, cited a paper, committed the
fix, verified the certificate — makoto holds that word against its record. If the deed isn't there,
or the verification was quietly disabled, makoto blocks the tool call (or the end-of-turn) and hands
the agent a one-line correction to retry against.

It judges the agent against its _own_ utterances and record — never the world's truth. It holds no
facts ("France doesn't exist to it"); it only checks that a claimed word is kept, whole, and honored
in deed. A word it lets through becomes spendable: trustworthy tender a reviewer or another agent can
accept without re-deriving it.

## What it catches

makoto fires on mechanical hook events — every `PreToolUse`, `PostToolUse`, and `Stop` — and **blocks**
(exit 2, which Claude Code treats as block-and-retry) on **18 pre-checks** across four families and
**8 end-of-turn gates**. Every live check blocks; there is no silent "warning" tier (see

View full repository on GitHub →