websiteURL should be present for marketplace readiness.
Craft
drobins25/craft · v2.9.0 · Development & Workflow
A Claude Code plugin that acts as an intelligent harness for your development workflow: your codebase is read-only by default, every change passes through a Write Gate as planned and approved work, and craft tracks your project's history, design tokens, and decisions locally so Claude learns your taste and architectural preferences over time
Guard checks the skills and MCP servers a plugin adds on your machine and asks you before a risky action runs. The scores above are free, and no plan changes them.
Is Craft a fit?
From the plugin's manifest and HOL's scan. Anything the plugin does not declare is shown as not declared.
Works with
- Claude Code
- 11 skills
- 1 MCP server
Before you install
- Sign-in
- Not declared
- Declared access
- Not declared
- License
- MIT
Check before relying on it
- Some security checks did not finish: Cisco skill scan and HOL plugin scan. See the evidence
- 3 medium findings from the scan. See the evidence
- The publisher has not verified ownership on HOL.
What is Craft?
Craft is a published development & workflow plugin for AI coding agents in the Claude Code ecosystem, developed by drobins25 and distributed through the HOL AI plugin registry. A Claude Code plugin that acts as an intelligent harness for your development workflow: your codebase is read-only by default, every change passes through a Write Gate as planned and approved work, and craft tracks your project's history, design tokens, and decisions locally so Claude learns your taste and architectural preferences over time.
- Canonical slug
- drobins25/craft
- Version
- v2.9.0 · updated Oct 15, 2026
- Open data
- entity.json (JSON-LD)
Registry snapshot
- Repository
- https://github.com/drobins25/craft
- Canonical profile
- https://hol.org/registry/plugins/drobins25%2Fcraft
- Owner verification
- Not verified
- Scanner
- Registry fallback scan
- Security result
- Caution
- Digest verified
- Yes
Trust and security
Trust & reputation
HOL Trust Score
Per-metric points (0–100 each) combined via a weighted average into the overall score.
Provenance
- Plugin root
- .
- Source repo
- https://github.com/drobins25/craft
- Source commit
- 1fbc2e858b22…
- Publisher verified
- No
- Owner verified
- Not owner verified
Continuous scanner CI not detected
This plugin remains listed. Its overall trust score is reduced by 10% because security checks are not maintained in the source repository's CI.
Optional: maintain the scanner in the source repository's CI to receive the full trust score. Listing does not require that change.
README badge not detected
Plugin owners can add the HOL badge to the repository README from Guard Plugins. Distribution, not security evidence. It adds a 2% engagement adjustment to the overall trust score and never changes the security result.
Security posture
See how the Trust Score is computed- Provider
- registry-broker-fallback
- Grade
- F · caution
- Version
- Unknown
Published advisories
None matched in GitHub security advisories, checked . This covers published advisories only, not problems nobody has reported.
GitHub security advisories are those the source repository has published.
Findings
privacyPolicyURL should be present for marketplace readiness.
termsOfServiceURL should be present for marketplace readiness.
Repository snapshot does not include a lockfile.
Cisco skill scanner exited with code 1: Error loading skill: No SKILL.md and no .md files found in /tmp/hol-skill-safety-RwLC3r (lenient mode requires at least one markdown file)
Cisco skill scanner exited with code 1: Error loading skill: No SKILL.md and no .md files found in /tmp/hol-skill-safety-Xh9lEL (lenient mode requires at least one markdown file)
Cisco skill scanner exited with code 1: Error loading skill: No SKILL.md and no .md files found in /tmp/hol-skill-safety-Y8UEtk (lenient mode requires at least one markdown file)
Cisco skill scanner exited with code 1: Error loading skill: No SKILL.md and no .md files found in /tmp/hol-skill-safety-esCHOL (lenient mode requires at least one markdown file)
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner exited with code 1: Error loading skill: No SKILL.md and no .md files found in /tmp/hol-skill-safety-oIImN9 (lenient mode requires at least one markdown file)
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner exited with code 1: Error loading skill: No SKILL.md and no .md files found in /tmp/hol-skill-safety-6DwDNw (lenient mode requires at least one markdown file)
Cisco skill scanner timed out after 60000 ms
Cisco skill scanner exited with code 1: Error loading skill: No SKILL.md and no .md files found in /tmp/hol-skill-safety-WdBodC (lenient mode requires at least one markdown file)
Cisco skill scanner exited with code 1: Error loading skill: No SKILL.md and no .md files found in /tmp/hol-skill-safety-cI5mMi (lenient mode requires at least one markdown file)
Install guidance
Install in Claude Code
Install through the Claude Code plugin marketplace.
Optional: install HOL Guard for Claude Code first, so it can check this plugin's tools on your machine before Claude Code uses them.
- 1
Add the marketplace
Run this inside a Claude Code session. It registers the marketplace manifest shipped at the repository root. If the repository ships none, add the generated entry from the Advanced section below first.
claude code - 2
Find the marketplace and plugin names
The install id is <plugin-entry>@<marketplace-name>, and the marketplace name is declared inside the manifest — it can differ from the repository name. List registered marketplaces to read both names.
shell - 3
Install the plugin
Substitute the plugin entry name and the marketplace name shown by the previous step.
claude code
Did setup work in Claude Code?
No setup reports for Claude Code yet. Self-reported by signed-in visitors. Copying a command is not counted, and most installs are never reported.
Attested installs: Fewer than 10 attested installs of this plugin in week 2026-W43, so no number is shown. Counted from opt-in HOL Guard install reports, once per machine and runtime, and never mixed with the answers above. How install reports work.
Loading reviews
Plugin manifest
{
"name": "craft",
"displayName": "craft",
"version": "2.9.0",
"description": "A Claude Code plugin that acts as an intelligent harness for your development workflow: your codebase is read-only by default, every change passes through a Write Gate as planned and approved work, and craft tracks your project's history, design tokens, and decisions locally so Claude learns your taste and architectural preferences over time.",
"author": {
"name": "Darin Drobinski",
"url": "https://github.com/drobins25"
},
"homepage": "https://github.com/drobins25/craft",
"repository": "https://github.com/drobins25/craft",
"license": "MIT",
"keywords": [
"claude-code",
"development",
"workflow",
"creative",
"harness",
"agents",
"multi-agent",
"orchestration",
"write-gate",
"quality-gates",
"taste"
],
"interface": {
"displayName": "craft",
"developerName": "drobins25"
},
"skills": "./",
"mcpServers": "./.registry/mcp.json",
"holManifestOrigin": "repository",
"registryIndexVersion": 5
}Marketplace source
- Repo URL
- https://github.com/drobins25/craft
- Marketplace path
- Unknown
- Source path
- .
- Install policy
- Unspecified
Skills
11 SKILL.md files ship with this plugin. Preview, copy, or download each one, then install them with the Skills CLI.
skills/adhoc/SKILL.md
Adhoc workflow for small targeted changes to existing behavior or appearance, without the full story ceremony. Use when the orchestrator encounters a bug with a clear root cause and surgical solution, OR a small enhancement to something already built (a different icon, wording, spacing, color). Triggers on: 'fix this', 'this is broken', 'the alignment is off', 'that button doesn't work', 'quick fix', 'patch this', 'tweak this', 'change the icon', 'adjust the wording', post-story corrections, or any situation where the write gate blocks a small targeted change. Acts NOW - a defect to file and fix later belongs in /craft:bugs, other deferred work in the notebook. Do NOT use for new features, design exploration, or changes requiring creative spark.
SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.
skills/approve/SKILL.md
Request write permission from the user before making file changes. MUST be invoked before any write attempt when the write gate is closed. Creates scoped approval via AskUserQuestion + TaskCreate, opens the write gate, and closes it when work is done. Triggers: write hook blocks an edit, agent is about to write files outside .craft/, agent needs to modify project source files. This skill requires user approval 100% of the time - never bypass AskUserQuestion.
SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.
skills/browser/SKILL.md
Interactive browser automation via playwright-cli. Use when you need to navigate a site, click elements, fill forms, take snapshots, or triage a live app.
SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.
skills/content-spark/SKILL.md
This skill should be used when a story has been captured but content direction is unresolved - the spark describes WHAT to build structurally but not WHAT goes in it. Reads the story spark, splits it into Resolved (structurally clear) vs. Assumed (would have to guess) content dimensions, and surfaces each assumption for the human to confirm, correct, or expand. Also classifies implementation risk tags (has-variants, has-data-pipeline, has-animation, has-touch-targets, diverges-from-existing) so plan-chunks translates them into acceptance criteria that name the implementation mechanism. Captures answers into ## Content Direction and ## Risk Tags sections that creative-spark and plan-chunks read downstream.
SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.
skills/creative-spark/SKILL.md
This skill should be used when the user asks to "brainstorm", "explore options", "get creative", "what if we...", or selects "Let's get creative" during story or cycle creation. NOT for a bare vague feature idea where generating options would mean inventing the premise first - that routes to /craft:riff (riff first, options after). Generates 3-4 creative options with trade-offs, visual direction for UI stories, and wireframes.
SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.
skills/design-vibe/SKILL.md
Use this skill when the user wants to discover, define, or refine their product's aesthetic identity. Triggers on "what should this feel like?", "help me figure out the vibe", "something feels off visually", "I want it to feel like [X]", "define the visual language", or when a project has no established design direction. This is the art director skill - it helps users articulate something they can feel but can't name. Also handles quick cohesion checks when the orchestrator needs one during cycle planning.
SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.
skills/lock-decision/SKILL.md
This skill should be used when the user says "lock it", "go with that", "approved", "that's the standard", or explicitly establishes a project-wide pattern like "from now on all forms should use this approach". Formalizes approved decisions into locked standards that the system enforces going forward. Not needed for story-scoped decisions — only for project-wide patterns.
SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.
skills/plan-chunks/SKILL.md
This skill should be used when the user asks to "plan chunks", "break this down", "plan the implementation", or when a story has status planning and needs implementation details before building. Required before any story can be implemented. Transforms story sparks into detailed chunk-by-chunk implementation plans with full technical specifics, file lists, and risk analysis. Supports parallel planning of multiple stories via batch mode.
SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.
skills/refine-chunk/SKILL.md
This skill should be used when validate-chunk reports errors or failures, when the user asks to "fix these errors", "resolve validation issues", "refine this chunk", or when specific build, lint, or type errors need surgical fixes. Makes precise, targeted edits to resolve specific validation issues without over-engineering.
SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.
skills/test-fix/SKILL.md
This skill should be used when validate-chunk reports test failures specifically, when the user says "tests are failing", "figure out what's wrong with the tests", "fix the failing tests", or when test assertions don't match expected output after chunk implementation. Triages whether the test or the implementation is wrong and fixes the correct one.
SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.
skills/validate-chunk/SKILL.md
Enforcement layer for chunk and story validation. Invokes the chunk-validator agent (haiku), enforces the verdict, routes failures to refine-chunk or test-fix, captures CLI learnings. The orchestrator invokes this skill — never the agent directly.
SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.
File inventory
.claude-plugin/plugin.json
file
864 bytes
10084dc8c459ca4c…
.codex-plugin/plugin.json
plugin-manifest
925 bytes
8c85c8cc3024bdbd…
.mcp.json
file
173 bytes
bec5a6b0e7fdd158…
.registry/mcp.json
mcp-config
129 bytes
0341150899b9972c…
agents/alchemist.md
file
33,824 bytes
a04f88174d7cb225…
agents/become-researcher.md
file
12,316 bytes
0d604811c43ef9d4…
agents/chunk-validator.md
file
18,373 bytes
c9ab9ce782e0ec4f…
agents/claims-auditor.md
file
5,442 bytes
4a60382e9c4b6bbe…
agents/conductor.md
file
26,000 bytes
7664be51a2c5e329…
agents/creative-analyzer.md
file
11,865 bytes
7f4f658eef4f8b0d…
agents/crystallizer.md
file
25,806 bytes
4c329a5e5b9291de…
agents/doc-writer.md
file
23,875 bytes
5dbe563a6cc15d0e…
agents/guide.md
file
12,169 bytes
c3ae92d058125aa9…
agents/implementer.md
file
29,005 bytes
f1e96850be19aa35…
agents/maze-architect.md
file
9,196 bytes
8949b17f3fb63fcf…
agents/muse.md
file
24,143 bytes
7e49afe92aaaa910…
agents/plan-chunks-agent.md
file
59,663 bytes
43625abad8f097fb…
agents/playwright-browser.md
file
11,075 bytes
31840593bd72b3f6…
agents/pr-reviewer-expert.md
file
14,648 bytes
9d08a1c6328da81a…
agents/practitioner-reviewer.md
file
5,681 bytes
3bfab2f0c16bbb17…
agents/product-anthropologist.md
file
28,093 bytes
3506038083b2919a…
agents/project-scanner.md
file
18,569 bytes
c8ea90e8d72e86ad…
agents/qa-analyzer.md
file
12,725 bytes
b0346b14c7d80f55…
agents/research-synthesizer.md
file
13,572 bytes
0da75a1c00a6f034…
agents/researcher.md
file
6,245 bytes
976e3e4ff227e72b…
agents/riff.md
file
26,144 bytes
05f021be545c9605…
agents/style-analyzer.md
file
13,445 bytes
9bd5c0ece24f4fd4…
agents/tester.md
file
9,057 bytes
edd65d5bdc9c960d…
agents/ux-analyzer.md
file
13,085 bytes
cb217e3248e22da3…
agents/verifier.md
file
5,949 bytes
492045303ca2e9f4…
agents/walkthrough-analyzer.md
file
15,579 bytes
d2016892b549f2b0…
CLAUDE.md
file
2,863 bytes
91f57d8c9a0abd52…
commands/craft-analyze.md
file
20,461 bytes
eadf04d3ac1586f7…
commands/craft-annotate.md
file
2,491 bytes
3deaa2d8a6dd4a83…
commands/craft-ask.md
file
5,535 bytes
0ef784da48bdf862…
commands/craft-become.md
file
20,167 bytes
520e587ae3b9ab06…
commands/craft-bugs.md
file
3,348 bytes
9a997d1c5556f239…
commands/craft-cycle-assign.md
file
5,802 bytes
2d830eaa45e40ef4…
commands/craft-cycle-complete.md
file
7,559 bytes
110d9d8ed064a3b8…
commands/craft-cycle-design.md
file
14,311 bytes
5d62a65bac54feee…
commands/craft-cycle-start.md
file
12,018 bytes
33fa32959b39958d…
commands/craft-dashboard.md
file
6,066 bytes
e7c5e127830808ec…
commands/craft-decisions.md
file
41,429 bytes
f7c97eb4d4e9c124…
commands/craft-dial.md
file
2,612 bytes
d855ad809342d8e6…
commands/craft-docs.md
file
12,842 bytes
bec4dae3a2b5141c…
commands/craft-guide.md
file
2,398 bytes
1317c5b3e715bedb…
commands/craft-init.md
file
69,866 bytes
5452dd2bfd0808c1…
commands/craft-mockup.md
file
2,102 bytes
eed794a05d06679a…
commands/craft-notebook.md
file
23,065 bytes
eafdd99a14bda3d4…
commands/craft-planning.md
file
24,961 bytes
cf2ef5b6554bc577…
commands/craft-project.md
file
2,875 bytes
5b664e092c02a017…
commands/craft-reflect.md
file
11,433 bytes
0eb927bffd7e1fc7…
commands/craft-research-verify.md
file
11,792 bytes
2d0f465799dcf515…
commands/craft-research.md
file
17,950 bytes
76d37adabf33bccc…
commands/craft-review.md
file
15,630 bytes
138f30203b107874…
commands/craft-riff.md
file
8,683 bytes
6d87c772e5db5262…
commands/craft-status.md
file
11,235 bytes
4cfef4be4edf2ccf…
commands/craft-story-archive.md
file
1,619 bytes
25a8df1873da7aee…
commands/craft-story-continue.md
file
5,026 bytes
c47e5cf8bcf03fc7…
commands/craft-story-delete.md
file
1,732 bytes
f59a2f0bc758efad…
commands/craft-story-implement-auto.md
file
6,413 bytes
bcd918835504f3bf…
commands/craft-story-implement.md
file
53,105 bytes
16a69dc28e672b6c…
commands/craft-story-new.md
file
25,655 bytes
2af1132449868daa…
commands/craft-update-docs.md
file
6,702 bytes
82d69c4dbaf2902d…
commands/craft-workflow-design.md
file
15,136 bytes
5e3aa7a5d06d8a2c…
commands/craft-workflow-run.md
file
24,185 bytes
3f23a57c50ca2e7e…
commands/craft-workflow.md
file
9,528 bytes
ccab9ed42cb3e829…
commands/craft.md
file
25,173 bytes
4bc30cdddbd3ebb0…
commands/references/agent-finding-handoff.md
file
7,808 bytes
f47bd7836f6d6997…
commands/references/alignment-check.md
file
20,784 bytes
ab985dec4b7153d8…
commands/references/analysis-bug-filing.md
file
6,929 bytes
d2bae5e77c74b3d1…
commands/references/annotate-inline.md
file
24,386 bytes
e4d53bc45b1ceb73…
commands/references/annotate-overlay.md
file
56,568 bytes
4aafe0cdaa3b3c1b…
commands/references/auq-grammar.md
file
6,402 bytes
1012d778ed90f543…
commands/references/bugs-record.md
file
8,558 bytes
4964dc99d51e9108…
commands/references/content-spark-inline.md
file
6,203 bytes
74fdacd72a515891…
commands/references/creative-spark-inline.md
file
6,371 bytes
1e0865a713e7a8d6…
commands/references/crystallize-expert.md
file
6,802 bytes
9104e1bcaddb2fc3…
commands/references/cycle-design/default-mode.md
file
30,352 bytes
adcdc3e3f4060f67…
commands/references/cycle-design/detailing-mode.md
file
8,446 bytes
9fe36e7bf6c60102…
commands/references/cycle-design/roadmap-mode.md
file
6,180 bytes
87d247c7fbf4fbc4…
commands/references/dial-inject.md
file
8,849 bytes
e8d54cdb82a80e95…
commands/references/dial-inline.md
file
16,376 bytes
81c83a60b10b17e7…
commands/references/doc-standards.md
file
5,957 bytes
272ed5691c00c25c…
commands/references/gate-reconcile.md
file
8,113 bytes
2673aed5ddb7966d…
commands/references/insight-mining.md
file
9,977 bytes
ba5241127bea7e0a…
commands/references/learnings-schema.md
file
3,052 bytes
853526c0223d4ee8…
commands/references/map-for-agents.md
file
6,077 bytes
e1acd292791144e1…
commands/references/map.md
file
3,543 bytes
6c7f7f84c62f370e…
commands/references/mockup-inline.md
file
39,537 bytes
c12947c1f1796669…
commands/references/mockup-muse-path.md
file
5,829 bytes
0ba4cbf71780b34f…
commands/references/muse-inline.md
file
8,324 bytes
215267855715c739…
commands/references/observations-surfacing.md
file
5,397 bytes
7ebe93411968e0cd…
commands/references/research-branch-template.md
file
8,173 bytes
75106213f40112af…
commands/references/rule-pass.md
file
5,900 bytes
f210b9a8b63ee59f…
commands/references/story-from-annotate.md
file
8,101 bytes
130ab481c28397e2…
commands/references/story-from-craft-designs.md
file
4,491 bytes
ea3316df875ff9e3…
commands/references/story-from-mockup.md
file
6,566 bytes
263ebd1e73797a5e…
commands/references/story-from-planning.md
file
30,660 bytes
f0c17132c3dd8493…
commands/references/taste-pass-disable.md
file
1,868 bytes
c49e124344ba4730…
Craft — Frequently asked questions
- What is Craft?
- Craft is an AI plugin in the HOL registry. A Claude Code plugin that acts as an intelligent harness for your development workflow: your codebase is read-only by default, every change passes through a Write Gate as planned and approved work, and craft tracks your project's history, design tokens, and decisions locally…
- How do I install Craft?
- Install Craft in your harness: Claude Code — /plugin marketplace add drobins25/craft; Any agent — npx [email protected] add drobins25/craft. Full step-by-step guidance is on the HOL plugin page.
- How do I install Craft in Claude Code?
- To install Craft in Claude Code, start with /plugin marketplace add drobins25/craft. The complete step-by-step install guide for Claude Code is on the HOL plugin page.
- How is the Trust Score for Craft computed?
- Craft has a HOL Trust Score of 59 out of 100. The score is a weighted sum of six components from a static scan of the source, capped for high-severity findings and adjusted by two disclosed policies. Memberships and payments are not inputs, and a scan is not a safety guarantee. Full breakdown: https://hol.org/registry/plugins/drobins25%2Fcraft/trust
- Who publishes Craft?
- Craft is published by drobins25 and listed on HOL.
Install signal
HOL cannot see every install. These are separate signals from different sources, so they are not added together. Counts under each floor show as <N.
- Install commands issued here
- <5
- HOL Guard install commands issued from this listing, last 28 days.
- Opt-in install reports
- <10
- Machines that reported installing it through HOL Guard in week 2026-W43. Reporting is opt-in, so most installs are not counted.
- HOL Guard workspaces
- <5
- Workspaces that approved it or include it in an approved-plugin feed, as of today.
Related plugins
Ordered by Trust Score. Listings cannot pay for these positions. Check each one fits your task before switching from Craft.
Alternatives in Development & Workflow
- agent-kitExtension pack of slash commands, skills, rules, and hooks adding plan-driven, confirmation-gated coding and staging-to-prod git workflows to Cursor and Claude CodeTrust 97 · Scan: passed · Codex, Claude Code, Cursor
- A TeamA complete engineering team in one folder with 26 specialist agents, 20 workflow skills, an orchestrator, and quality gates; integration and hook support vary by coding platform.Trust 96 · Scan: passed · Codex, Claude Code, Cursor
- ArmorCodexIntent-based security for Codex with MCP plan registration, policy gating, CSRG cryptographic proofs, and audit logging on `bash` and `apply_patch`.Trust 96 · Scan: passed · MCP, Codex
- AtomLaneParallelizes only work proven safe by compiling resource-aware atomic plans for builds, tests, Make/Compose workflows, and long-running jobs with live progress and measured savings.Trust 96 · Scan: passed · Codex
Reviews and similar plugins
User reviews
No reviews yet. Write the first review
Similar plugins
Similar by contents
Suggested from HOL scan evidence: same category, at least one shared runtime, similar tags and contents. Paid placement and Trust Score play no part.
