A

Agent Face

ericphamhoangdev/agent-face · v0.2.2 · Tools & Integrations

by ericphamhoangdevOwner verifiedScan grade: GoodAwesome AI Plugins

Agent skills that give a coding agent a small always-on-top desktop face showing its state (working, thinking, happy, stuck) with captions and lip-synced voice clips

Follow0
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 Agent Face a fit?

From the plugin's manifest and HOL's scan. Anything the plugin does not declare is shown as not declared.

Works with

  • Agent Plugin
  • Claude Code
  • 4 skills

Before you install

Sign-in
Not declared
Declared access
Not declared
License
MIT

Check before relying on it

What is Agent Face?

Agent Face is a published tools & integrations plugin for AI coding agents that works with Agent Plugin and Claude Code, developed by ericphamhoangdev and distributed through the HOL AI plugin registry. Agent skills that give a coding agent a small always-on-top desktop face showing its state (working, thinking, happy, stuck) with captions and lip-synced voice clips.

Canonical slug
ericphamhoangdev/agent-face
Version
v0.2.2 · updated Nov 2, 2026

Registry snapshot

Owner verification
Verified on HOL as @ericphamhoangdev
Marketplace source
.claude-plugin/marketplace.json
Scanner
HOL plugin scanner
Security result
Needs review
Digest verified
Yes
4 bundled skillsRead, copy or download each SKILL.mdOpen skills

Trust and security

Trust & reputation

On-Chain Verified
78

HOL Trust Score

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

Installability
100/100
Maintenance
65/100
MCP server setup
100/100
Plugin Security
82/100
Provenance
80/100
Publisher Quality
100/100

Provenance

Plugin root
.
Source repo
https://github.com/ericphamhoangdev/agent-face-skills
Source commit
2c227c3b59f3…
Publisher verified
Yes
Owner verified
@ericphamhoangdev
Agent Plugins 1.0
Ready (structural check)

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.

Needs review
Security result
82
Security score
0
High findings
Provider
codex-plugin-scanner
Grade
B · Good
Version
3.24.2
codex:hol-plugin-scanner-FGzyWE / cisco-skill-scanner: timed_outcodex:hol-plugin-scanner-FGzyWE / cisco-mcp-scanner: skipped

[claude:.] Claude Plugin

22/22

5 checks

[claude:.] Security

13/16

6 checks

[claude:.] Operational Security

0/6

5 checks

[claude:.] Code Quality

10/10

2 checks

[codex:.] Manifest Validation

25/31

9 checks

[codex:.] Security

13/16

9 checks

[codex:.] Operational Security

0/6

5 checks

[codex:.] Best Practices

9/12

5 checks

[codex:.] Marketplace

15/15

3 checks

[codex:.] Skill Security

5/5

4 checks

[codex:.] 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

mediumoperational-securityDEPENDENCY_LOCKFILE_MISSINGReported 2 times

package.json is present without a corresponding lockfile or pinned dependency snapshot.

Commit a lockfile or use fully pinned requirements for reproducible dependency resolution.

lowsecuritySECURITY_MD_MISSINGReported 2 times

Plugins should publish a SECURITY.md file for responsible disclosure and support guidance.

Add a SECURITY.md file with reporting guidance and supported versions.

lowoperational-securityDEPENDABOT_MISSINGReported 2 times

Automation or dependency surfaces exist, but .github/dependabot.yml is missing.

Add Dependabot updates for GitHub Actions and dependency manifests.

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 agent-face entry from the agent-face-skills 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 agent-face@agent-face-skills.

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

{
  "$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",
  "name": "agent-face",
  "version": "0.2.2",
  "description": "Give a coding agent a floating desktop face with visual states, custom templates, and voice clips.",
  "author": {
    "name": "ericphamhoangdev",
    "url": "https://github.com/ericphamhoangdev"
  },
  "homepage": "https://github.com/ericphamhoangdev/agent-face-skills",
  "repository": "https://github.com/ericphamhoangdev/agent-face-skills",
  "license": "MIT",
  "keywords": [
    "agent",
    "desktop",
    "face",
    "voice"
  ],
  "extensions": {
    "com.openai": {
      "interface": {
        "displayName": "Agent Face",
        "shortDescription": "A floating desktop face for coding agents.",
        "longDescription": "Show a coding agent's current state in an always-on-top desktop window, customize its visual templates, and play voice clips with lip-sync.",
        "developerName": "ericphamhoangdev",
        "category": "Developer Tools",
        "websiteURL": "https://github.com/ericphamhoangdev/agent-face-skills",
        "defaultPrompt": [
          "Set up a face for this coding agent.",
          "Show the agent face and set it to the working state."
        ]
      }
    }
  },
  "interface": {
    "displayName": "agent-face",
    "developerName": "ericphamhoangdev"
  },
  "skills": "./",
  "holManifestOrigin": "repository",
  "registryIndexVersion": 9
}

Marketplace source

Repo URL
https://github.com/ericphamhoangdev/agent-face-skills
Marketplace path
.claude-plugin/marketplace.json
Source path
.
Install policy
Unspecified

Skills

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

Share
skills-cli
  • repo-safety-scan

    .claude/skills/repo-safety-scan/SKILL.md

    Scan this repo for secrets, security problems and personal details, in the staged changes, the working tree, or every commit in its history (file contents, file names, author and committer emails, messages), and fix what it finds. Use before every git commit, before pushing or making the repo public, when the user asks whether the repo is safe to share or publish, and whenever a secret or personal detail may have been committed.

    SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.

  • agent-face-template

    skills/agent-face-template/SKILL.md

    Create or change your face templates, meaning the sub-folders of .agent-face/ in your repo that hold the state images, lip-sync mouth frames and voice clips. Use when the user wants a new face or another look, new or changed states or expressions, animated states, a talking mouth, voice clips added or lip-sync tuned; when moving templates over from the old Agent Face MCP app or from the agent-face/ folder of version 0.1; and whenever face.cjs check reports problems. Needs the agent-face skill installed next to it.

    SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.

  • agent-face-voice

    skills/agent-face-voice/SKILL.md

    Speak through your face by playing one of its voice clips out loud, with the mouth moving in time. Use when the user asks you to say something aloud, to greet them, or to announce that long work has finished; when they ask about your voice, muting or volume; and when a state should make a sound. Needs the agent-face skill installed next to it.

    SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.

  • agent-face

    skills/agent-face/SKILL.md

    Give yourself a floating face on the user's desktop and keep it in step with what you are doing, with no MCP server. Use at the start and end of every turn to set the face's state (working, thinking, happy…) and an optional caption; whenever the user mentions your face, avatar or expression, asks you to show, hide, switch or fix it, or asks to see your face in the chat; to list your face templates and their states and voice clips; and for first-time setup. Your face templates live in your own repo (.agent-face/); this skill ships the window and the face.cjs command that drives it.

    SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.

File inventory

.agents/plugins/marketplace.json

file

369 bytes

b6e29d690f108ce7…

.claude-plugin/marketplace.json

file

608 bytes

a930e355e843a128…

.claude/skills/repo-safety-scan/personal-terms.example.json

file

437 bytes

5134e21c71dcfc78…

.claude/skills/repo-safety-scan/references/security-checklist.md

file

3,894 bytes

6d5aa1826978b7a4…

.claude/skills/repo-safety-scan/scripts/scan.cjs

file

32,760 bytes

85d0f1266afbb574…

.claude/skills/repo-safety-scan/SKILL.md

skill

8,545 bytes

5376a6b212130fd6…

.codex-plugin/plugin.json

plugin-manifest

1,192 bytes

13a58f3423b70ff0…

LICENSE

file

1,452 bytes

a3831afb5c8d3863…

package.json

file

371 bytes

52b2d688d8ee6a79…

plugin.json

file

1,254 bytes

d33fc04c9d15cf43…

README.md

file

12,501 bytes

c52d087be80feaf0…

skills/agent-face-template/references/making-art.md

skill

6,235 bytes

e69328e325d74d88…

skills/agent-face-template/references/template-format.md

skill

3,553 bytes

83d4d963b369f910…

skills/agent-face-template/SKILL.md

skill

6,345 bytes

5009fe79fcefb0fc…

skills/agent-face-voice/SKILL.md

skill

4,824 bytes

f05fa4916b54b868…

skills/agent-face/lib/config.cjs

skill

5,048 bytes

34165ea91462a8a0…

skills/agent-face/lib/ipc.cjs

skill

1,515 bytes

ca7055ae67c5157b…

skills/agent-face/lib/media.cjs

skill

5,339 bytes

277f26c9e3a726e6…

skills/agent-face/lib/paths.cjs

skill

3,952 bytes

0395112e051f88c9…

skills/agent-face/lib/starter.cjs

skill

4,208 bytes

ed8333dc110b531a…

skills/agent-face/lib/store.cjs

skill

1,305 bytes

62bf3414d6c22d9c…

skills/agent-face/runtime/face.css

skill

3,379 bytes

558b51f882d4151b…

skills/agent-face/runtime/face.js

skill

13,422 bytes

93f15f2e8c3db270…

skills/agent-face/runtime/lipsync.js

skill

4,122 bytes

f3d8f18ca677983d…

skills/agent-face/runtime/main.cjs

skill

23,311 bytes

4c93e32cb78f15c1…

skills/agent-face/runtime/package.json

skill

169 bytes

7196397ded591158…

skills/agent-face/runtime/page.cjs

skill

1,540 bytes

8efd8f070c7fa338…

skills/agent-face/runtime/preload.cjs

skill

857 bytes

ba0af2943a6c385c…

skills/agent-face/scripts/face.cjs

skill

21,125 bytes

c11acb5dbd7d3dbb…

skills/agent-face/SKILL.md

skill

7,687 bytes

0b3bbb95877e165b…

Agent Face — Frequently asked questions

What is Agent Face?
Agent Face is an AI plugin in the HOL registry. Agent skills that give a coding agent a small always-on-top desktop face showing its state (working, thinking, happy, stuck) with captions and lip-synced voice clips.
How do I install Agent Face?
Install Agent Face in your harness: Claude Code — /plugin marketplace add ericphamhoangdev/agent-face-skills; Any agent — npx [email protected] add ericphamhoangdev/agent-face-skills. Full step-by-step guidance is on the HOL plugin page.
How do I install Agent Face in HOL Guard?
To install Agent Face in HOL Guard, start with hol-guard plugin install ericphamhoangdev/agent-face --apply. The complete step-by-step install guide for HOL Guard is on the HOL plugin page.
How do I install Agent Face in Claude Code?
To install Agent Face in Claude Code, start with /plugin marketplace add ericphamhoangdev/agent-face-skills. The complete step-by-step install guide for Claude Code is on the HOL plugin page.
How is the Trust Score for Agent Face computed?
Agent Face has a HOL Trust Score of 78 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/ericphamhoangdev%2Fagent-face/trust
Who publishes Agent Face?
Agent Face is published by ericphamhoangdev 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