claude

zeugnis

Audits code that looks right and is not, and counts a finding only after an independent pass has re-checked it.

1 on GitHubby Anselm Hahnv2.0.0MITupdated 12 days agodevelopment
/

Plugin zeugnis from marketplace werkstoff in Anselmoo/werkstoff. Commands read from the repo's manifest — 11 days ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (9)

  • zeugnis-agentic-reliability

    Use when the user asks to audit this plugin repository's own skill, agent, or workflow definitions for agentic-loop reliability defects, wants to check for unbounded retries, missing escalation paths, unwired Find/Verify phases, or excessive tool grants, or asks 'is our own agent design safe'. Verif

  • zeugnis-assertion-audit

    Use when the user asks whether their test suite would actually catch bugs, wants a mutation-testing pass over target source and test files, asks to check for weak or tautological assertions, or wants zeugnis's assertion audit run. Not for proving that a specific change, fix, wire, or numeric claim i

  • zeugnis-code-change

    Use when the user asks for a pre-commit quality check on staged or uncommitted changes, wants a quick zeugnis pass over 'what I just changed' before committing, or asks 'is this diff okay to commit'. Only runs the domains whose file patterns match the changed files, and always produces an advisory v

  • zeugnis-contract-drift

    Use when the user asks to audit type signatures, docstrings, or API/OpenAPI/GraphQL schemas against actual call-site or handler usage, wants to check for contract drift after a refactor, or wants zeugnis's contract-drift audit run. Scope is structural, machine-checkable declarations only. Not for pr

  • zeugnis-cycle

    Use when the user asks for a bounded self-optimization loop that re-runs zeugnis's audits until convergence or a pass cap, wants to 'run the zeugnis cycle', 'keep fixing findings until done', or asks for propose-only vs fix-mode passes. Runs at most max_passes_per_invocation (default 5) passes, appl

  • zeugnis-dependency-audit

    Use when the user asks to audit declared dependencies for hallucinated, nonexistent, or typosquat-adjacent packages, wants zeugnis's dependency audit run, or asks whether package.json/requirements.txt/pyproject.toml/Cargo.toml/go.mod/Gemfile entries actually exist. Performs bounded, read-only regist

  • zeugnis-mutation-harden

    Use when the user wants a REAL mutation tool run over one module or package, the surviving mutants triaged, and tests written that kill them -- 'harden these tests with mutmut', 'raise the mutation score of this module', 'run mutation testing and kill the survivors'. Runs the tool on fresh git-archi

  • zeugnis-preflight

    Use when the user asks whether this repository is ready for zeugnis audits to run successfully, wants a pre-flight/readiness check before running zeugnis-dependency-audit, zeugnis-assertion-audit, zeugnis-contract-drift, or zeugnis-agentic-reliability, or asks 'is zeugnis set up correctly here'. Run

  • zeugnis-status

    Use when the user asks where zeugnis's quality analysis stands, which reports are stale, what to run next, or wants a dashboard of all findings so far. Read-only: never triggers an audit itself, only reports on what has already run.

Subagents (6)

  • agentic-reliability-auditor

    Use this agent to find agentic-loop reliability defects in a plugin repository's own skill, agent, and workflow definitions: unbounded retry loops, absent escalation paths, Find phases with no adversarial Verify wiring, and tool grants that exceed an agent's stated role. Read-only — it never propose

  • assertion-auditor

    Use this agent to check whether a test suite would actually catch bugs, by proposing plausible small mutations to target source (off-by-one, boundary flip, condition negation) and judging whether existing tests would catch each one. Operates in Find, Verify, or Suggest mode depending on the dispatch

  • contract-auditor

    Use this agent to find drift between machine-checkable contracts — type hints, function signatures, docstring parameter/return descriptions, and API/OpenAPI/GraphQL schemas — and their actual call-site or handler usage. Operates in Find (extract contracts and compare) or Verify (independently re-che

  • dependency-auditor

    Use this agent to check whether declared dependencies in manifest files actually exist in their public registries, flagging packages that appear hallucinated (nonexistent) or typosquat-adjacent to a popular package. Performs read-only registry lookups only, via the plugin's bounded-timeout lookup sc

  • mutation-killer

    Use this agent when zeugnis-mutation-harden dispatches one lane -- one module, one budget -- of surviving or untested mutants that a real mutation tool reported, to write tests that assert real values so each mutant would fail them, or to classify a mutant as equivalent with a one-line reason. Write

  • zeugnis-remediator

    Use this agent when a single, already-located zeugnis finding (a hallucinated/typosquat dependency-manifest entry, a contract-declaration mismatch, or an excessive-tool-grant in an agent's frontmatter) needs exactly one scoped fix applied and nothing else. Always dispatched once per finding by zeugn

Hooks (2)

  • PreToolUse

    python3 -B "${CLAUDE_PLUGIN_ROOT}/scripts/hooks/guard_edit_scope.py"

  • PreToolUse

    python3 -B "${CLAUDE_PLUGIN_ROOT}/scripts/hooks/guard_bash_scope.py"

View source on GitHub anselmoo.github.io

More from Anselmoo/werkstoff

All 14 plugins →

befund

claude

Makes a codebase describe its own health, with every finding tied to file:line evidence, and edits source only behind an authorization recorded on disk.

16 skills · 11 agents · hooks

1

Turns a described change into a budgeted workflow, builds it several independent ways at once, and lands exactly one result.

10 skills · 12 agents · hooks

1

cupertino

claude

A design and craft discipline rooted in Steve Jobs' documented decisions, run as a fixed lifecycle of stages from experience to ship, not a menu of design techniques.

16 skills · 4 agents · hooks

1

lehre

claude

Researches a code style, pattern and architecture doctrine, then denies the write that would violate it.

9 skills · 9 agents · hooks

1

matrize

claude

Derives a design system once from reference exemplars you admire, names every element, and emits it to any target.

12 skills · 6 agents · hooks

1

zirkel

claude

Makes sure a complex or ambiguous task is clarified, explored and decomposed before anyone starts executing it.

14 skills · 3 agents

1

Similar plugins

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

context7

claudecodex

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.

1 MCP server

upstash/context7 64,709

Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.

5 commands

HKUDS/CLI-Anything 58,665

Automates browser interactions for web testing, form filling, screenshots, and data extraction

12 skills

vercel-labs/agent-browser 50,373

Use Alibaba Open Code Review from local Codex.

2 skills

alibaba/open-code-review 50,068

slidev

claude

Claude Code skill for creating and presenting Slidev slidedecks

1 skill

slidevjs/slidev 49,452

Maintain zeugnis?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins14 plugins