📋
AI EngineeringGo

H-Spec

by m0n0x41d

H-Spec is an AI Engineering skill for Claude Code, published by m0n0x41d in haft.

1.4K stars102 forkson m0n0x41d/haftAdded 2026/08/19Repository updated 2026/08/11
ai-agentsai-codinganthropicclaudeclaude-codecodexcontext-memorycursorcursor-aideveloper-toolsfirst-principlesgemini-clihuman-ai-collaborationmcpreasoningspec-driven-developmentsystems-engineering
Install in seconds
Install H-Spec
Copy H-Spec into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/m0n0x41d/haft/tree/main/internal/cli/skill/h-spec ~/.claude/skills/h-spec

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/m0n0x41d/haft.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
internal/cli/skill/h-spec/SKILL.md in m0n0x41d/haft
Installs to
~/.claude/skills/h-spec
Collection
One of 24 skills cataloged from this repository
Category
AI Engineering2451 skills

What H-Spec does

H-Spec manages 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, updates, stale sections, newer source revisions, or semantic changes across carriers.

H-Spec is cataloged under AI Engineering on DirSkills. H-Spec comes from a repository tagged ai-agents, ai-coding, anthropic, claude and claude-code.

Documentation

README

h-spec — Typed spec lifecycle and semantic repair

Keep object, description, carrier, and authority separate:

  • object: the system, behavior, role, boundary, or term being described;
  • description: the SpecSection claim;
  • carrier: .haft/specs/*.md and its fenced block;
  • lifecycle authority: the kernel projection plus explicit human gates.

TargetSystemSpec, SoftwareSystemSpec, and related carrier names are Haft local-practice concepts. Do not attribute a target system vs enabling system kind distinction to FPF A.1. When FPF precision is needed, recover the actual holon/system, context, transformation, role, method, WorkPlan, and Work relations from the source.

Conditional project-memory orientation

This is the opening of the README. Read the full README on GitHub.

Frequently asked about H-Spec

  • What else does m0n0x41d publish alongside H-Spec?

    H-Spec is one of 24 skills that DirSkills catalogs from m0n0x41d/haft, the repository it ships in. Its siblings there include Decision Verification, H Explore and H Status. Each one is a separate skill with its own page in this directory, installs the same way H-Spec does, and is maintained by m0n0x41d in that same repository. The rest of the collection is listed on the m0n0x41d/haft page.

  • How does H-Spec compare to other AI Engineering skills?

    H-Spec ranks #1057 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of H-Spec against them. Open each page to compare what they document and how they install.

More from m0n0x41d/haft

H-Spec is one of 24 skills cataloged on DirSkills from m0n0x41d/haft.

See all 24 skills
🔎
2w ago

Decision Verification

Decision Verification checks whether a recorded DecisionRecord still holds by running baseline vs measure evidence loops and drift detection. Use it when a shipped decision needs a post-implementation reality-check before further work relies on it.
Quality
1.4K102
🧭
2w ago

H Explore

H Explore generates 3-5 genuinely distinct candidate approaches for a current question, keeping the weakest link of each visible. Use it when alternatives are needed or a favored approach is prematurely closing the search.
AI Engineering
1.4K102
📊
2w ago

H Status

H Status reports read-only project memory and coverage from a current code index, including active problems, decisions, notes, evidence freshness, drift, and file-link gaps. Use it for project status, session resumption, or answering what is decision-linked, uncovered, or needs attention.
Data
1.4K102
🔍
2w ago

H Verify

H Verify compares recorded DecisionRecords or claims against current code, tests, measurements, or incidents to surface weakened, refuted, stale, or drifted claims. Use it when design-time claims need runtime evidence before relying on them.
Quality
1.4K102
🛡️
2w ago

H-Commission

H-Commission creates a WorkCommission grant from an active DecisionRecord only when manually invoked by an operator. It verifies source decision status and freshness, derives execution scope, snapshots the autonomy envelope, and stops before any execution.
AI Engineering
1.4K102
🛂
2w ago

H-Commission

H-Commission creates bounded execution authority from an explicit operator grant and never auto-triggers or infers approval from prompt text or tool schemas. Use it when an agent needs a manual human gate before executing scoped actions.
AI Engineering
1.4K102