loom-code-skill icon

loom-code-skill

clickhouse/loom-code-skill · v1.3.0 · Development & Workflow

by ClickHouseAwesome AI Plugins

MCP server: self-hosted shared long-term memory, document search with citations (PDF, .docx, .pptx) and a code index of your repositories (definitions, callers, change impact) for AI agents, with data stored in ClickHouse and plugins for Claude Code and Codex

Protect this install with HOL Guard

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 loom-code-skill 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
  • MCP
  • Antigravity CLI
  • Cursor
  • Agent Plugin
  • 29 skills

Before you install

Sign-in
Not declared
Declared access
Not declared
License
Apache-2.0

Check before relying on it

  • Some security checks did not finish: Cisco skill scan. See the evidence
  • 2 high or critical findings from the scan. See the evidence
  • The publisher has not verified ownership on HOL.

What is loom-code-skill?

loom-code-skill is a published development & workflow plugin for AI coding agents that works with Claude Code, MCP, Antigravity CLI, Cursor and Agent Plugin, developed by ClickHouse and distributed through the HOL AI plugin registry. MCP server: self-hosted shared long-term memory, document search with citations (PDF, .docx, .pptx) and a code index of your repositories (definitions, callers, change impact) for AI agents, with data stored in ClickHouse and plugins for Claude Code and Codex.

Canonical slug
clickhouse/loom-code-skill
Version
v1.3.0 · updated Nov 20, 2026

Registry snapshot

Owner verification
Not verified
Marketplace source
.claude-plugin/marketplace.json
Scanner
HOL plugin scanner
Security result
Partial scan
Digest verified
Yes
29 bundled skillsRead, copy or download each SKILL.mdOpen skills

Trust and security

Trust & reputation

39

HOL Trust Score

Per-metric points (0–100 each) combined via a weighted average into the overall score.

Installability
100/100
Maintenance
100/100
MCP server setup
100/100
Plugin Security
93/100
Provenance
70/100
Publisher Quality
75/100

Provenance

Plugin root
.
Source repo
https://github.com/ClickHouse/loom
Source commit
e50ca4a235d7…
Publisher verified
No
Owner verified
Not owner verified
Agent Plugins 1.0
Ready (structural check)

Continuous scanner CI detected

No action is required. This plugin receives the full trust score.

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.

Partial scan
Security result
93
Score from finished checks
2
High findings

Some checks did not finish: Cisco skill scan. No blocking issue was found in the checks that did finish, but this is not a passed scan.

Provider
codex-plugin-scanner
Grade
A · Excellent
Version
3.24.2
codex:hol-plugin-scanner-2fqukA / cisco-skill-scanner: failedcodex:hol-plugin-scanner-2fqukA / cisco-mcp-scanner: skipped

[claude:.] Claude Plugin

18/18

5 checks

[claude:.] Security

16/16

6 checks

[claude:.] Operational Security

6/6

5 checks

[claude:.] Code Quality

10/10

2 checks

[codex:.] Manifest Validation

25/31

9 checks

[codex:.] Security

16/16

9 checks

[codex:.] Operational Security

6/6

5 checks

[codex:.] Best Practices

9/12

5 checks

[codex:.] Marketplace

15/15

3 checks

[codex:.] Skill Security

0/5

4 checks

[codex:.] Code Quality

10/10

2 checks

[gemini:.] Gemini Extension

10/10

3 checks

[gemini:.] Security

16/16

6 checks

[gemini:.] Operational Security

6/6

5 checks

[gemini:.] Code Quality

10/10

2 checks

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

highskill-securityRISKY_SKILL_INSTRUCTION

The skill includes "curl -s "http://loom:loomdev@localhost:18123/?query=SELECT+count()+FROM+system.tables+WHERE+database=" and uses curl with uploads, shell composition, or arguments requiring review.

Remove instructions that read sensitive local files, launch shell wrappers, or send workspace data to remote endpoints.

highskill-securityRISKY_SKILL_INSTRUCTION

The skill includes "curl -fsSL https://github.com/ClickHouse/loom/releases/latest/download/install.sh" and uses curl with uploads, shell composition, or arguments requiring review.

Remove instructions that read sensitive local files, launch shell wrappers, or send workspace data to remote endpoints.

infomanifest-validationPLUGIN_JSON_INTERFACE_SHORTDESCRIPTION

The interface object is missing a valid "shortDescription" value.

Add a valid "shortDescription" field to the interface metadata.

infomanifest-validationPLUGIN_JSON_INTERFACE_LONGDESCRIPTION

The interface object is missing a valid "longDescription" value.

Add a valid "longDescription" field to the interface metadata.

infomanifest-validationPLUGIN_JSON_INTERFACE_CATEGORY

The interface object is missing a valid "category" value.

Add a valid "category" field to the interface metadata.

infomanifest-validationPLUGIN_JSON_INTERFACE_CAPABILITIES

The interface object is missing a valid "capabilities" value.

Add a valid "capabilities" field to the interface metadata.

infomanifest-validationPLUGIN_JSON_INTERFACE_ASSET_WEBSITEURL

The interface field "websiteURL" must use HTTPS or point to a safe in-repo asset.

Update "websiteURL" to use HTTPS or an existing relative asset path.

infomanifest-validationPLUGIN_JSON_INTERFACE_ASSET_PRIVACYPOLICYURL

The interface field "privacyPolicyURL" must use HTTPS or point to a safe in-repo asset.

Update "privacyPolicyURL" to use HTTPS or an existing relative asset path.

infomanifest-validationPLUGIN_JSON_INTERFACE_ASSET_TERMSOFSERVICEURL

The interface field "termsOfServiceURL" must use HTTPS or point to a safe in-repo asset.

Update "termsOfServiceURL" to use HTTPS or an existing relative asset path.

infomanifest-validationPLUGIN_JSON_INTERFACE_ASSET_COMPOSERICON

The interface field "composerIcon" must use HTTPS or point to a safe in-repo asset.

Update "composerIcon" to use HTTPS or an existing relative asset path.

infomanifest-validationPLUGIN_JSON_INTERFACE_ASSET_LOGO

The interface field "logo" must use HTTPS or point to a safe in-repo asset.

Update "logo" to use HTTPS or an existing relative asset path.

infomanifest-validationPLUGIN_JSON_INTERFACE_ASSET_SCREENSHOTS

The interface field "screenshots" must use HTTPS or point to a safe in-repo asset.

Update "screenshots" to use HTTPS or an existing relative asset path.

infobest-practicesCODEXIGNORE_MISSING

A .codexignore file helps prevent accidental inclusion of local artifacts and secrets.

Add a .codexignore file with generated assets, local state, and secret paths.

Install guidance

Install in Claude Code

Install through the Claude Code plugin marketplace.

Claude Code plugin docs

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. 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. 2

    Install the plugin

    Installs the loom-code-skill entry from the loom marketplace.

    claude code
  3. 3

    Scripted alternative

    Non-interactive equivalent for scripts and CI pipelines. Add --scope project to pin the install to one repository.

    shell
  4. 4

    Check it is installed

    Lists installed plugins. The entry should appear as enabled.

    shell

To remove it later, run claude plugin uninstall loom-code-skill@loom.

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-W46, 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": "loom-code-skill",
  "version": "1.3.0",
  "description": "Code search and code intelligence for repositories in a Loom code index (the loom-code Agent Skill: code.* first, then read only that), and the loom Agent Skill: how an agent uses Loom. Skills only, no hooks.",
  "author": {
    "name": "ClickHouse"
  },
  "homepage": "https://clickhouse.github.io/loom/",
  "repository": "https://github.com/ClickHouse/loom",
  "license": "Apache-2.0",
  "keywords": [
    "code-intelligence",
    "code-search",
    "agent-memory",
    "mcp",
    "clickhouse",
    "agent",
    "skill"
  ],
  "displayName": "ClickHouse Loom skills",
  "icon": "./integrations/claude-code-plugin/assets/icon.png",
  "interface": {
    "displayName": "ClickHouse Loom skills",
    "developerName": "ClickHouse"
  },
  "skills": "./",
  "holManifestOrigin": "repository",
  "registryIndexVersion": 9
}

Marketplace source

Repo URL
https://github.com/ClickHouse/loom
Marketplace path
.claude-plugin/marketplace.json
Source path
.
Install policy
Unspecified

Skills

29 SKILL.md files ship with this plugin. Preview, copy, or download each one, then install them with the Skills CLI.

Share
skills-cli
  • loom-address-review

    .claude/skills/loom-address-review/SKILL.md

    Works through review comments on your own Loom PR — verifies each thread, fixes it or answers why not, replies with the fixing commit, and repeats until a fresh review is empty. Use for "address the review", requested changes, or reviewer or bot comments on your PR. Not for reviewing others' changes (loom-review).

    Raw SKILL.md
  • loom-bench

    .claude/skills/loom-bench/SKILL.md

    Runs and reports a Loom benchmark — when a paid run is allowed, which harness answers the question, proving the treatment ran, judging a delta against noise. Use when asked to benchmark, measure recall or answer accuracy, A/B a setting, or update docs/benchmarks/results.md. Not for test or CI speed.

    Raw SKILL.md
  • loom-change

    .claude/skills/loom-change/SKILL.md

    Lists what else a Loom change must touch in the same PR (generated files, snapshots, erasure classification, docs, manifests) for a new or changed op, field, table, column, migration, setting, flag, worker, provider, CLI command, plugin hook or dashboard page. Use before editing for any of those.

    Raw SKILL.md
  • loom-debug

    .claude/skills/loom-debug/SKILL.md

    Finds the cause of a Loom bug before any edit — failing cases from evidence (request id, loom.agent_events, system.query_log, search traces), their pattern, a hypothesis, then a test that fails first. Use when an op, worker, search result or test behaves wrongly. Not for a red CI job (loom-investigate-ci).

    Raw SKILL.md
  • loom-deploy

    .claude/skills/loom-deploy/SKILL.md

    Operator procedure for a blue/green Loom deployment with redeploy.sh — preflight, swap, post-swap checks, rollback. Use only when an operator explicitly asks to deploy, roll back or check which build is serving.

    Raw SKILL.md
  • loom-dev-setup

    .claude/skills/loom-dev-setup/SKILL.md

    Sets up an isolated Loom environment for one task — a worktree from origin/main, its own virtualenv, its own ClickHouse on free ports, migrations, a server from source. Use when starting a Loom change, or when asked to run the server or the integration tests locally.

    Raw SKILL.md
  • loom-file-issue

    .claude/skills/loom-file-issue/SKILL.md

    Files or updates a Loom GitHub issue — duplicate check, a reproduction with versions, the matching issue form and label, a redacted body. Use when asked to open, file or report an issue, bug, regression or feature request, or to add findings to one. Not for security reports (SECURITY.md).

    Raw SKILL.md
  • loom-investigate-ci

    .claude/skills/loom-investigate-ci/SKILL.md

    Takes a failing Loom CI check to its cause and fix — the failed log, whether main fails too, a local reproduction. Use when a PR check is red, a PR shows no checks, a job looks flaky, or when asked why CI fails. Not for bugs found outside CI (loom-debug).

    Raw SKILL.md
  • loom-pre-push

    .claude/skills/loom-pre-push/SKILL.md

    Runs the Loom CI gates a diff touches, locally, and fixes each failure at its source — format, lint, generator checks, ratchets, unit tests, schema, frontend, plugins, integration. Use before a commit or push, after a rebase, or when asked "is this ready". Not for opening the PR (loom-ship-pr).

    Raw SKILL.md
  • loom-release

    .claude/skills/loom-release/SKILL.md

    Cuts and checks a Loom release — the version bump and notes (prepare.py), the release PR, a release candidate and its soak, the final tag and the registry dispatch, then the release checked from outside (one-line installer on amd64 and arm64, SDK installs, anonymous pulls, signatures), rollback and patch releases. Use when asked to release, tag, publish or verify a release.

    Raw SKILL.md
  • loom-review

    .claude/skills/loom-review/SKILL.md

    Reviews a Loom PR or diff against Loom's invariants and area rules and for needless complexity, verifying each finding before reporting it with severity and file:line. Use when asked to review a PR, branch or diff, or to post review comments. After your own push, start the loom-reviewer agent instead.

    Raw SKILL.md
  • loom-ship-pr

    .claude/skills/loom-ship-pr/SKILL.md

    Opens and lands a Loom PR — signed-off commits, a public body from the template, a fresh review at every push alongside CI, a CI gate on gh's JSON, and a squash merge on green. Use when asked to open, update, land or merge a PR. Comments on it — loom-address-review; a red check — loom-investigate-ci.

    Raw SKILL.md
  • loom-writing

    .claude/skills/loom-writing/SKILL.md

    Plain technical English for commit messages, PR and issue text, review comments and replies, code comments and docs, with a checker for filler words and internal details. Use before writing or posting any of them, or when asked to make text read less generated. Owns wording, not sections.

    Raw SKILL.md
  • improve-loom-for-my-repo

    integrations/claude-code-plugin/skills/improve-loom-for-my-repo/SKILL.md

    >

    Raw SKILL.md
  • loom-code

    integrations/claude-code-plugin/skills/loom-code/SKILL.md

    >

    Raw SKILL.md
  • loom-memory

    integrations/claude-code-plugin/skills/loom-memory/SKILL.md

    >

    Raw SKILL.md
  • loom-mentor

    integrations/claude-code-plugin/skills/loom-mentor/SKILL.md

    >

    Raw SKILL.md
  • loom-optimize

    integrations/claude-code-plugin/skills/loom-optimize/SKILL.md

    >

    Raw SKILL.md
  • loom-session

    integrations/claude-code-plugin/skills/loom-session/SKILL.md

    >

    Raw SKILL.md
  • loom-status

    integrations/claude-code-plugin/skills/loom-status/SKILL.md

    >

    Raw SKILL.md
  • improve-loom-for-my-repo

    integrations/codex-plugin/skills/improve-loom-for-my-repo/SKILL.md

    >

    Raw SKILL.md
  • loom-code

    integrations/codex-plugin/skills/loom-code/SKILL.md

    >

    Raw SKILL.md
  • loom-memory

    integrations/codex-plugin/skills/loom-memory/SKILL.md

    >

    Raw SKILL.md
  • loom-mentor

    integrations/codex-plugin/skills/loom-mentor/SKILL.md

    >

    Raw SKILL.md
  • loom-optimize

    integrations/codex-plugin/skills/loom-optimize/SKILL.md

    >

    Raw SKILL.md
  • loom-session

    integrations/codex-plugin/skills/loom-session/SKILL.md

    >

    Raw SKILL.md
  • loom-status

    integrations/codex-plugin/skills/loom-status/SKILL.md

    >

    Raw SKILL.md
  • loom-code

    skills/loom-code/SKILL.md

    Route-then-read code intelligence for a loom-indexed repository. WHEN: the repo is indexed by loom (LOOM_BASE_URL set, or a `.loom` marker), and you would otherwise read whole files, grep the tree, or guess who calls a function. Use loom's code.* tools to find the exact unit first, then read only that. FOR SINGLE OPERATIONS: call the code.* MCP tool directly.

    Raw SKILL.md
  • loom

    skills/loom/SKILL.md

    How an agent uses Loom: memory, documents, working state, runs and code intelligence that persist across sessions and are shared with other agents. WHEN: you have a Loom server (LOOM_BASE_URL, an SDK `Agent`, `loom_*` MCP tools) and you start a task, learn a durable fact, hold a document or a large blob, need to resume, hand work to another agent, or answer from what an earlier session knew. Covers MCP, the Python and TypeScript SDKs and plain HTTP.

    Raw SKILL.md

File inventory

.agents/plugins/marketplace.json

file

373 bytes

68e48913fd19c953…

.claude-plugin/marketplace.json

file

1,661 bytes

9d15bdc13019e510…

.claude-plugin/plugin.json

file

667 bytes

f74b0ec3386dd73c…

.claude/skills/loom-address-review/evals/triggers.json

file

705 bytes

e3d927bab53fecb9…

.claude/skills/loom-address-review/SKILL.md

skill

3,699 bytes

9e3fa16eeebc2422…

.claude/skills/loom-bench/evals/triggers.json

file

694 bytes

172f74c95a4b9068…

.claude/skills/loom-bench/SKILL.md

skill

4,518 bytes

b1e9dcfa02b68d0e…

.claude/skills/loom-change/evals/triggers.json

file

657 bytes

d93c992152755f02…

.claude/skills/loom-change/SKILL.md

skill

5,155 bytes

15ca487f596f0f45…

.claude/skills/loom-debug/evals/triggers.json

file

717 bytes

3cd6ac433dbd3cc6…

.claude/skills/loom-debug/SKILL.md

skill

3,773 bytes

23f649c5b079ee46…

.claude/skills/loom-deploy/agents/openai.yaml

file

208 bytes

e732e0bd1b954526…

.claude/skills/loom-deploy/evals/triggers.json

file

503 bytes

cf26d72a3b01130a…

.claude/skills/loom-deploy/SKILL.md

skill

3,853 bytes

7a4af238dabf54d8…

.claude/skills/loom-dev-setup/evals/triggers.json

file

546 bytes

e6332cc73bcd4487…

.claude/skills/loom-dev-setup/SKILL.md

skill

7,671 bytes

b79ef325fee365ef…

.claude/skills/loom-file-issue/evals/triggers.json

file

731 bytes

8cef84734ccafffd…

.claude/skills/loom-file-issue/SKILL.md

skill

4,968 bytes

de77f79b2bb2d165…

.claude/skills/loom-investigate-ci/evals/triggers.json

file

605 bytes

a00d9786239b9d36…

.claude/skills/loom-investigate-ci/SKILL.md

skill

8,736 bytes

b6e950f8afc60e12…

.claude/skills/loom-pre-push/evals/triggers.json

file

522 bytes

7370dccf15a09918…

.claude/skills/loom-pre-push/SKILL.md

skill

8,737 bytes

45600db7fc8866df…

.claude/skills/loom-release/evals/triggers.json

file

822 bytes

ad6550e4e05eead6…

.claude/skills/loom-release/SKILL.md

skill

15,526 bytes

650950f7c00a35fd…

.claude/skills/loom-review/evals/triggers.json

file

556 bytes

b46fd9f2409c3328…

.claude/skills/loom-review/SKILL.md

skill

5,992 bytes

5de9e295f216b631…

.claude/skills/loom-ship-pr/evals/triggers.json

file

611 bytes

88563d07a827acc8…

.claude/skills/loom-ship-pr/SKILL.md

skill

6,328 bytes

0c5c7ff2bc995f15…

.claude/skills/loom-writing/evals/triggers.json

file

683 bytes

bded1a80e23ac22e…

.claude/skills/loom-writing/scripts/check_prose.py

file

5,277 bytes

2c29e1411050fefb…

.claude/skills/loom-writing/SKILL.md

skill

4,969 bytes

30949a4709cc7c77…

.codex-plugin/plugin.json

plugin-manifest

770 bytes

603279f96bdd9d2b…

.cursor-plugin/marketplace.json

file

466 bytes

15d486d239e9bfb3…

.cursor-plugin/plugin.json

file

1,273 bytes

ceb54ebb3495d789…

.github/dependabot.yml

file

335 bytes

9e2fb8fc9b8cdbc9…

AGENTS.md

file

7,925 bytes

fd49e422895fff7a…

biome.json

file

1,495 bytes

d52a29090f973ad0…

CLAUDE.md

file

380 bytes

5ccf70bd66e77acd…

gemini-extension.json

file

875 bytes

b6728283c7476e5c…

integrations/claude-code-plugin/skills/improve-loom-for-my-repo/SKILL.md

skill

4,083 bytes

36ff695f31c2a473…

integrations/claude-code-plugin/skills/loom-code/reference.md

file

7,188 bytes

239612a4d3ae6cdb…

integrations/claude-code-plugin/skills/loom-code/SKILL.md

skill

3,679 bytes

a17538bd5cf4787e…

integrations/claude-code-plugin/skills/loom-memory/reference.md

file

10,638 bytes

6ea9df0cdc0eb698…

integrations/claude-code-plugin/skills/loom-memory/SKILL.md

skill

5,007 bytes

a99856abb3fdc5f6…

integrations/claude-code-plugin/skills/loom-mentor/reference.md

file

13,306 bytes

ed9bf8266a627fa1…

integrations/claude-code-plugin/skills/loom-mentor/SKILL.md

skill

3,999 bytes

f5678a431eea8f47…

integrations/claude-code-plugin/skills/loom-optimize/reference.md

file

3,645 bytes

a065b7d7ce9e1494…

integrations/claude-code-plugin/skills/loom-optimize/SKILL.md

skill

5,934 bytes

a2e01eb1425a9aca…

integrations/claude-code-plugin/skills/loom-session/SKILL.md

skill

3,982 bytes

5474d61ba9bd519a…

integrations/claude-code-plugin/skills/loom-status/reference.md

file

3,965 bytes

0451c49ac155bfca…

integrations/claude-code-plugin/skills/loom-status/scripts/ensure-node.sh

file

7,202 bytes

739100fe48a9aba4…

integrations/claude-code-plugin/skills/loom-status/SKILL.md

skill

3,983 bytes

a860589fddd49754…

integrations/codex-plugin/skills/improve-loom-for-my-repo/SKILL.md

skill

4,083 bytes

36ff695f31c2a473…

integrations/codex-plugin/skills/loom-code/reference.md

file

7,188 bytes

239612a4d3ae6cdb…

integrations/codex-plugin/skills/loom-code/SKILL.md

skill

3,679 bytes

a17538bd5cf4787e…

integrations/codex-plugin/skills/loom-memory/reference.md

file

10,638 bytes

6ea9df0cdc0eb698…

integrations/codex-plugin/skills/loom-memory/SKILL.md

skill

5,007 bytes

a99856abb3fdc5f6…

integrations/codex-plugin/skills/loom-mentor/reference.md

file

13,306 bytes

ed9bf8266a627fa1…

integrations/codex-plugin/skills/loom-mentor/SKILL.md

skill

3,999 bytes

f5678a431eea8f47…

integrations/codex-plugin/skills/loom-optimize/reference.md

file

3,645 bytes

a065b7d7ce9e1494…

integrations/codex-plugin/skills/loom-optimize/SKILL.md

skill

5,934 bytes

a2e01eb1425a9aca…

integrations/codex-plugin/skills/loom-session/SKILL.md

skill

3,982 bytes

5474d61ba9bd519a…

integrations/codex-plugin/skills/loom-status/reference.md

file

3,965 bytes

0451c49ac155bfca…

integrations/codex-plugin/skills/loom-status/scripts/ensure-node.sh

file

7,202 bytes

739100fe48a9aba4…

integrations/codex-plugin/skills/loom-status/SKILL.md

skill

3,983 bytes

a860589fddd49754…

LICENSE

file

15,092 bytes

86bb101e989cfa9f…

plugin.json

file

823 bytes

7d5daa62fb854bde…

pyproject.toml

file

17,854 bytes

6381eb0196083c1f…

README.md

file

22,061 bytes

853343f4472c220e…

SECURITY.md

file

8,522 bytes

55a1e7121e9e2c59…

skills/loom-code/SKILL.md

skill

4,754 bytes

0e30b6abbc91bcf5…

skills/loom/reference.md

skill

14,024 bytes

f17384cefb9cee4b…

skills/loom/SKILL.md

skill

15,605 bytes

69052846d33d8651…

uv.lock

file

785,785 bytes

ce7d5a1d2c89f154…

loom-code-skill — Frequently asked questions

What is loom-code-skill?
loom-code-skill is an AI plugin in the HOL registry. MCP server: self-hosted shared long-term memory, document search with citations (PDF, .docx, .pptx) and a code index of your repositories (definitions, callers, change impact) for AI agents, with data stored in ClickHouse and plugins for Claude Code and Codex.
How do I install loom-code-skill?
Install loom-code-skill in your harness: Claude Code — /plugin marketplace add ClickHouse/loom; Cursor — npx [email protected] add ClickHouse/loom; Antigravity CLI — npx [email protected] add ClickHouse/loom. Full step-by-step guidance is on the HOL plugin page.
How do I install loom-code-skill in HOL Guard?
To install loom-code-skill in HOL Guard, start with hol-guard plugin install clickhouse/loom-code-skill --apply. The complete step-by-step install guide for HOL Guard is on the HOL plugin page.
How do I install loom-code-skill in Claude Code?
To install loom-code-skill in Claude Code, start with /plugin marketplace add ClickHouse/loom. The complete step-by-step install guide for Claude Code is on the HOL plugin page.
How do I install loom-code-skill in Cursor?
To install loom-code-skill in Cursor, start with npx [email protected] add ClickHouse/loom. The complete step-by-step install guide for Cursor is on the HOL plugin page.
How is the Trust Score for loom-code-skill computed?
loom-code-skill has a HOL Trust Score of 39 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/clickhouse%2Floom-code-skill/trust
Who publishes loom-code-skill?
loom-code-skill is published by ClickHouse and listed on HOL.

Directory acceptance

Listed in 0 of 5 directory lists

Read from the list each directory publishes on GitHub. Being listed means the directory accepted the plugin; it is not a HOL security rating.

Lists last read . HOL re-reads them every day.

Submitting it? Check it against each directory's rules

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-W46. 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.

Reviews and similar plugins