> ## Documentation Index
> Fetch the complete documentation index at: https://hibi.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Hibi: Keep Docs and AI-Agent Instructions Up to Date

> Hibi tracks claims in docs and agent instruction files, anchors them to source code, and flags drift deterministically with no model in the check loop.

You change a constant in `src/auth.ts`. Two sentences in `README.md` and `CLAUDE.md` are now wrong, and nobody notices until a teammate or an agent trusts one of them. `hibi check --since origin/main` names those sentences and gives you the command to fix each.

Hibi (日々, "day after day") tracks **claims**: a sentence in a document, anchored to the code it describes. When either side changes, `hibi check` flags the claim and can stamp a status banner into the document, so a reader without hibi still sees the flag.

Run it in CI, in a git hook, or as the check an agent makes before it trusts an instruction file.

## The model

You record a claim with `hibi record`, pointing at a span of prose and the code span it describes. Hibi stores an **anchor** for each side (pointers, not a copy of the prose) in a committed `.claims/` directory, one file per claim.

On `hibi check`, each side is located again in the current files and graded as `unchanged`, `moved`, `changed`, `ambiguous`, or `orphaned`. An enforced claim **gates** (exit 2) when a side is `changed`, `orphaned`, or `ambiguous`, when its ttl passed, or when a verifier failed. `moved` is a warning. Every suspect verdict carries a remediation menu with the next command filled in.

<Note>
  No model runs in the check loop. The same working tree yields the same verdicts. A flag means re-verify; Hibi does not decide that a doc is wrong, and it never edits prose.
</Note>

## Start here

<CardGroup cols={2}>
  <Card title="Quickstart" icon="rocket" href="/quickstart">
    Install Hibi and record a claim.
  </Card>

  <Card title="Verdicts" icon="scale-balanced" href="/verdicts">
    The claim model, the anchor states, the remediation menu, and the exit codes.
  </Card>

  <Card title="Why Hibi" icon="compass" href="/design">
    The problem, the threat model, and why no model sits on the verdict path.
  </Card>

  <Card title="CLI reference" icon="terminal" href="/cli-reference">
    Every command and flag.
  </Card>

  <Card title="Resolvers" icon="puzzle-piece" href="/resolvers">
    Add out-of-process resolvers and verifier runners in any language.
  </Card>

  <Card title="Claude Code skill" icon="wand-magic-sparkles" href="/claude-code">
    The Agent Skill that teaches coding agents to use Hibi.
  </Card>
</CardGroup>

## What you can rely on

<CardGroup cols={2}>
  <Card title="Deterministic" icon="scale-balanced">
    The check loop runs text matching, tree-sitter, and fixed constants. No model.
  </Card>

  <Card title="A flag means re-verify" icon="flag">
    Hibi reports that the text or code under a claim moved. It does not declare a doc wrong.
  </Card>

  <Card title="Any file format" icon="file-lines">
    Docs are text. Markdown, plain text, AsciiDoc, and instruction files work without a per-format parser.
  </Card>

  <Card title="Offline and shallow-clone safe" icon="wifi-slash">
    The anchor is its own baseline. `check` reads files, not git history.
  </Card>
</CardGroup>