m0n0x41d/haft

Engineering decisions engine that know when they're stale. Frame, compare, decide — with evidence decay and parity enforcement. For Claude Code, Cursor, Gemini CLI, Codex and more.

This repository also configures its own agents. See what haft tells them →

1.4kStars on the repository
14Mods indexed here, across every type
24d agoLast push, which is what freshness is scored on
customA LICENSE file GitHub cannot name, so bodies are not copied

h-commission

01

m0n0x41d/haft

Skill Claude Code

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, snapshots the…

not rated 1.4k +1 24d ago A 103 tokens

h-compare

02

m0n0x41d/haft

Skill Claude Code

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 conversational comparison…

not rated 1.4k +1 24d ago A 110 tokens

h-decide

03

m0n0x41d/haft

Skill Claude Code

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.

not rated 1.4k +1 24d ago A 58 tokens

h-diagnose

04

m0n0x41d/haft

Skill Claude Code

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 ordinarily…

not rated 1.4k +1 24d ago A 95 tokens

h-explore

05

m0n0x41d/haft

Skill Claude Code

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, or other current…

not rated 1.4k +1 24d ago A 99 tokens

h-frame

06

m0n0x41d/haft

Skill Claude Code

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 ProblemCard only on explicit…

not rated 1.4k +1 24d ago A 99 tokens

h-note

07

m0n0x41d/haft

Skill Claude Code

A project-memory note for saving a fact, observation, caveat, or small reason for later use. It records the note only when explicitly requested or when a clear use for it exists.

not rated 1.4k +1 24d ago A 93 tokens

h-onboard

08

m0n0x41d/haft

Skill Claude Code

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 immediately after haft…

not rated 1.4k +1 24d ago A 79 tokens

h-reason

09

m0n0x41d/haft

Skill Claude Code

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 FPF source, inspect…

not rated 1.4k +1 24d ago A 112 tokens

h-spec

10

m0n0x41d/haft

Skill Claude Code

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 status", "update…

not rated 1.4k +1 24d ago A 124 tokens

h-status

11

m0n0x41d/haft

Skill Claude Code

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 uncovered", or "what needs…

not rated 1.4k +1 24d ago A 97 tokens

h-verify

12

m0n0x41d/haft

Skill Claude Code

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 stale", "measure…

not rated 1.4k +1 24d ago A 155 tokens

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: