claude

whetstone

Engineering-craft skills: red-green TDD, a flaky-test rate, diagnosis, doubt review, grilling, a merge check, grounded research reports, HTML reports, skill linting and a staged-diff column budget. TDD, the merge check, skill lint, column budget and HTML report end in a script's exit code; the flaky-test rate is computed and printed, and sets no exit code; doubt review, grilling, diagnosis and the research verdicts are model-judgment. Auto-composed by the dossier plugin at its phase gates when both are installed — fully functional standalone.

3 on GitHubby Mrugesh MohapatraISCupdated todayworkflow
/

Plugin whetstone from marketplace raisedadead-plugins in raisedadead/claude-code-plugins. Commands read from the repo's manifest — today.

What it installs

Skills (11)

  • codebase-design

    Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.

  • diagnose

    Diagnose a hard bug or a performance regression with a feedback loop first, then ranked hypotheses, instrumentation and a regression test. Use when the user says diagnose or debug this, or reports something broken, throwing, failing or slow.

  • domain-modeling

    Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR.

  • doubt-pass

    Adversarial doubt cycle on a plan or design before any code exists — distinct from post-hoc code review. Use when the user asks to doubt this, stress-test a design before building it, poke holes in a plan, find the flaw in an approach, or before committing to a non-trivial architecture or design dec

  • grill

    Interview the user about a plan, a design or a decision until every branch is settled, with a recommended answer for each question. Use when the user asks to be grilled, wants to stress-test an idea, or a request has several readings that change what gets built.

  • html-report

    Render a markdown report as one self-contained HTML page for a human reader, in plain English, with the answer first, a table of contents and Mermaid diagrams drawn as images. Use when the user asks for an HTML report, or for a readable page made from a markdown document.

  • prototype

    Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.

  • research-report

    Research a technical question with probes on the local system, a web fan-out through deep-research, a grounding pass on every load-bearing claim, and a report rendered as one HTML page. Use when the user asks for a research report, a design study or an evidence-backed recommendation about their own

  • skill-smith

    Lint and structure-check a SKILL.md — frontmatter, line budget, trigger clause, reference depth. Use when the user asks to write a new skill, review this skill, lint a SKILL.md, check skill frontmatter, or after editing any file under a skills/*/SKILL.md path.

  • tdd-cycle

    Drive one vertical slice of behaviour red-green-refactor, seam agreed before the first test. Use when the user asks to add a feature, fix a bug, write code test-first, says "TDD this", "red green refactor", or "write a failing test first". Inside a live dossier:build covenant, invoke dossier:build i

  • tiger-style

    Check the column budget of the lines a change adds, and read that change against the TIGER_STYLE shape rules a script cannot judge. Use when the user asks about line length or column limits, to check code shape, what the column check flagged, or why a commit was blocked on a column budget.

Subagents (4)

  • whetstone-doubter

    Fresh-context adversarial design reviewer for doubt-pass. Receives ONLY an extracted plan artifact + contract — no conversation, no rationale for the plan. Finds where the plan breaks, not whether it is good — or, on a subtraction mission, what can go. Read-only, apart from one notes file the missio

  • whetstone-grounder

    Adversarial verifier — takes a batch of claims, independently re-checks every cited source (URL, file:line or command), and rules each claim CONFIRMED, UNSUPPORTED, CONTRADICTED or SOURCE-DEAD. Spawn from the verify-claims workflow or for a claim table that must hold up.

  • whetstone-reviewer

    Fresh-context diff reviewer. Hunts invented APIs, unprobed claims, ceremony, test theater and OWASP-class defects in changed code, and returns one path:line finding per line and a REVIEW line. Read-only, apart from one notes file the mission names. Spawn for a review of a change, or from the lens-re

  • whetstone-scout

    Read-only research, apart from one notes file the mission names — gathers sourced claims from docs, specs, code and the web, and returns a claim table rather than conclusions. Spawn for a self-contained research question, or from the verify-claims workflow.

View source on GitHub

More from raisedadead/claude-code-plugins

All 2 plugins →

dossier

claude

Phase-scoped engineering workflow: single-file DOSSIER.md, cross-repo state, drift detection, resumable builds, evidence log. Composes the whetstone plugin at phase gates when installed (doubt, TDD proof, merge check, skill lint) — fully functional without it.

7 skills · 3 agents

3

Similar plugins

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

superpowers

claudecodex

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

15 skills · hooks

obra/superpowers 316,836

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

12 skills

vercel-labs/agent-browser 50,373

Perform AI code review on Git diffs — supports workspace changes, branch ranges, and single commits with concurrent per-file analysis, codebase search, and deep context-aware review.

2 commands

alibaba/open-code-review 50,068

Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development

9 skills · 1 command · 8 agents

wshobson/agents 42,461

beads

claudecodex

AI-supervised issue tracker for coding workflows

1 skill · 1 agent · hooks

gastownhall/beads 28,698

Maintain whetstone?

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 plugins2 plugins