claude

haft

FPF reasoning methodology for structured decision-making with auditable hypothesis-evidence trails (formerly quint)

3 on GitHubby Agustin Carrascov5.0.0updated 5 days ago
/

Plugin haft from marketplace asermax-plugins in asermax/claude-plugins. Commands read from the repo's manifest — 5 days ago.

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

What it installs

Skills (12)

  • h-commission

    Creates a WorkCommission — bounded execution authority — from an active DecisionRecord. MANUAL ONLY: operator must explicitly type /h-commission. Never auto-invoked: commissions are execution-authority grants under Transformer Mandate. Runs freshness check, scope check, derives an ImplementationPlan

  • h-compare

    Compare two or more existing candidates under an explicit characteristic space, parity basis, and predeclared selection policy. Return constraints, trade-offs, and a non-dominated set rather than hiding the choice in one score. This skill is independent of h-frame and h-explore. Default to a convers

  • h-decide

    Routes one direct, unambiguous operator request to bind a bounded choice as a DecisionRecord. Use when the operator asks to decide, bind, or supersede a choice; h-frame, h-explore, and h-compare are independent capabilities, not mandatory phases. The operator directly requests one binding effect wit

  • h-diagnose

    Diagnose a concrete failure with parallel rival-hypothesis testing. Use when symptoms are observable but cause is unclear. Stabilize the signal, generate distinct explanations, test them read-only in parallel, and rank by evidence while keeping losing rivals visible. This skill is independent and or

  • h-explore

    Generate 3-5 genuinely distinct candidate approaches for a current question, with the weakest link of each kept visible. Use when alternatives are needed or one favored approach is prematurely closing the search. This skill is independent: it may work from an inline question, cue, accepted problem,

  • h-frame

    Shape an engineering problem without assuming a solution or forcing a project phase. Use when a redesign, refactor, or proposal arrives before the affected object, observed signal, constraints, unresolved relation, and acceptance basis are clear. Default to a conversational frame; record a ProblemCa

  • h-note

    Persist a fact, observation, caveat, or small non-binding rationale in Haft project memory when the operator explicitly asks or current Work supplies a concrete operator-named or agent-inferred receiving use that needs a lightweight addressable fact. Use for "remember this", "запиши", or "note for l

  • h-onboard

    Bootstrap Haft through one readable onboarding surface, prepare an initial profile review or one bounded existing-scope relation change, and orient applicable specification carriers. Use for first-time setup, incomplete setup, or profile-underdetermined spec recovery. Project memory is ready immedia

  • h-reason

    Source-first umbrella for FPF-aware reasoning in a Haft project. Use when the operator asks to think through an ambiguous engineering, management, architecture, specification, or project question without naming a narrower Haft capability. Recover the current object and question, query the bundled FP

  • h-spec

    Manage Haft's typed specification lifecycle and source-currentness repair: inspect current SpecSections, draft or clarify carriers, classify FPF semantic fanout, record operator-requested spec changes, and cross explicit approve/rebaseline/reopen gates only with human authorization. Use for "spec st

  • h-status

    Read-only Haft project cockpit for active problems, decisions, notes, evidence freshness, drift, commissions, spec lifecycle, module decision coverage, and bounded exact file-link gaps from a current code index. Use for project status, session resumption, "what is decision-linked", "what is uncovere

  • h-verify

    Verifies that a recorded DecisionRecord still holds — baseline-vs-measure evidence loop with drift detection per FPF Evidence Decay. Make sure to use this skill whenever the user asks "did dec-X work", "is decision Y still valid", "did the prediction come true", "check if the migration held", "is X

MCP servers (1)

  • haft

    runs: ${CLAUDE_PLUGIN_ROOT}/bin/haft serve

Hooks (1)

  • SessionStart

    ${CLAUDE_PLUGIN_ROOT}/hooks/session-init.sh

View source on GitHub

Problems found in this repo's manifests

  • "openspec" points to ./openspec, which doesn't exist in the repo — install will fail

More from asermax/claude-plugins

All 12 plugins →

mahou

claude

Small, single-job software engineering skills where the human makes every decision and the agent executes: explore, shape, design, program architecture, blast radius, agentic and human review, documentation into the project's docs folder, and a wiki of distilled technical knowledge

43 skills · 14 agents

3

katachi

claude

Spec-driven development framework with iterative growth, progressive adoption, and retrofit support

32 skills · 13 agents

3

Curated development workflow skills for browser automation, documentation, and code directives

9 skills · 4 commands · 1 agent · hooks

3

zenku

claude

An Obsidian-vault quest log: journeys that clear unknown ground one question at a time, raids that build what they settled, and durable notes the project owns

15 skills

3

Secondary workflow skills and commands split out from superpowers: systematic debugging, agent communication, evolutionary algorithm discovery, and more

5 skills · 4 commands · hooks

3

annai

claude

Code review surface: agent skill generates a guided JSON view of a PR, local server renders it in the browser

4 skills

3

Maintain haft?

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 plugins12 plugins