A

Agent Replay

sangloo/replay · v0.1.0 · Development & Workflow

by sanglooScan grade: AcceptableAwesome AI Plugins

Replays Claude Code, Codex and Gemini CLI sessions change by change with the agent's own words above each step, flags what was not actually checked (failures hidden by a pipe, tests that lost assertions or gained a .skip, files changed after the last passing check), and installs as a Claude Code plugin with four skills and a capture-after-every-turn hook

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 Replay 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
  • Antigravity CLI
  • 4 skills

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. See the evidence
  • The publisher has not verified ownership on HOL.

What is Agent Replay?

Agent Replay is a published development & workflow plugin for AI coding agents that works with Claude Code and Antigravity CLI, developed by sangloo and distributed through the HOL AI plugin registry. Replays Claude Code, Codex and Gemini CLI sessions change by change with the agent's own words above each step, flags what was not actually checked (failures hidden by a pipe, tests that lost assertions or gained a .skip, files changed after the last passing check), and installs as a Claude Code plugin with four skills and a capture-after-every-turn hook.

Canonical slug
sangloo/replay
Version
v0.1.0 · updated Nov 2, 2026

Registry snapshot

Owner verification
Not verified
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

69

HOL Trust Score

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

Installability
100/100
Maintenance
0/100
MCP server setup
100/100
Plugin Security
76/100
Provenance
70/100
Publisher Quality
75/100

Provenance

Plugin root
plugin
Source repo
https://github.com/sangloo/agent-replay
Source commit
e20fcf7c17a7…
Publisher verified
No
Owner verified
Not owner verified
Agent Plugins 1.0
Not detected

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
76
Security score
0
High findings
Provider
codex-plugin-scanner
Grade
C · Acceptable
Version
3.24.2
codex:hol-plugin-scanner-PuCQu3 / cisco-skill-scanner: failedcodex:hol-plugin-scanner-PuCQu3 / cisco-mcp-scanner: skipped

[claude:.] Claude Plugin

18/18

5 checks

[claude:.] Security

10/16

6 checks

[claude:.] Operational Security

N/A

5 checks · not applicable

[claude:.] Code Quality

10/10

2 checks

[codex:.] Manifest Validation

21/31

9 checks

[codex:.] Security

10/16

9 checks

[codex:.] Operational Security

N/A

5 checks · not applicable

[codex:.] Best Practices

6/12

5 checks

[codex:.] Marketplace

N/A

3 checks · not applicable

[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

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.

lowsecurityLICENSE_MISSINGReported 2 times

Plugins should ship a LICENSE file so consumers can review usage rights.

Add a LICENSE file that matches the manifest license metadata.

lowbest-practicesREADME_MISSING

Plugins should document installation, usage, and security expectations in README.md.

Add a README.md that explains setup, usage, and operational constraints.

infomanifest-validationPLUGIN_JSON_RECOMMENDED_AUTHOR

The manifest is missing the documented recommended field "author".

Add "author" to strengthen the plugin manifest metadata.

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 replay entry from the agent-replay 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 replay@agent-replay.

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": "replay",
  "displayName": "Replay",
  "description": "Replay what a coding agent did, change by change: capture sessions with notes, review them against the evidence, and learn a repository through a course that rebuilds it from nothing.",
  "version": "0.1.0",
  "license": "MIT",
  "homepage": "https://github.com/sangloo/agent-replay",
  "repository": "https://github.com/sangloo/agent-replay",
  "keywords": [
    "review",
    "replay",
    "code-review"
  ],
  "interface": {
    "displayName": "Replay",
    "developerName": "sangloo"
  },
  "skills": "./",
  "holManifestOrigin": "repository",
  "registryIndexVersion": 9
}

Marketplace source

Repo URL
https://github.com/sangloo/agent-replay
Marketplace path
.claude-plugin/marketplace.json
Source path
plugin
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
  • replay-history

    skills/replay-history/SKILL.md

    Replay a repository's git history change by change — a range of commits, or a codebase introduced file by file in reading order — and add notes that explain each commit. Use when someone wants to understand how code evolved, review a range of commits, or catch up on what changed since a release.

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

  • replay-review

    skills/replay-review/SKILL.md

    Review what a coding agent did in a session — replay it, check the evidence (which tests and checks ran, whether they held, what changed after them), flag the risky steps with notes, and hand the reviewer one file to open. Use when asked to review an agent's work, a session, a branch an agent wrote, or "what did it actually do".

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

  • replay-teach

    skills/replay-teach/SKILL.md

    Teach a repository by rebuilding it from nothing as a course — lessons that write the real code a piece at a time, with explanations of the design, the functions and the mathematics beside it, playable in the replay player. Use when someone wants to learn or onboard onto a codebase (especially one written largely by AI) without replaying every commit, or asks to "teach me", "walk me through", "explain this repo" or "make a course".

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

  • replay

    skills/replay/SKILL.md

    Save this agent session as a replay a reviewer can play back change by change, with notes on the parts that need a careful look and a check of the evidence. Use at the end of any session that changed code — before or instead of a PR — or when the user asks to "capture", "save", "record" or "replay" the session. Works for Claude Code, Codex and Gemini CLI sessions alike.

    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

463 bytes

2c67e8fde36b6292…

.codex-plugin/plugin.json

plugin-manifest

562 bytes

606c9029f189e42b…

hooks/hooks.json

file

302 bytes

8c90d67b28c2edc4…

skills/replay-history/SKILL.md

skill

2,188 bytes

1760f9215a7f6a1f…

skills/replay-review/SKILL.md

skill

3,209 bytes

890aedc2e1af8753…

skills/replay-teach/SKILL.md

skill

9,650 bytes

b91a0e8e35785946…

skills/replay/SKILL.md

skill

4,835 bytes

a05f936aceada53b…

Agent Replay — Frequently asked questions

What is Agent Replay?
Agent Replay is an AI plugin in the HOL registry. Replays Claude Code, Codex and Gemini CLI sessions change by change with the agent's own words above each step, flags what was not actually checked (failures hidden by a pipe, tests that lost assertions or gained a .skip, files changed after the last passing check),…
How do I install Agent Replay?
Install Agent Replay in your harness: Claude Code — /plugin marketplace add sangloo/agent-replay; Antigravity CLI — npx [email protected] add sangloo/agent-replay; Any agent — npx [email protected] add sangloo/agent-replay. Full step-by-step guidance is on the HOL plugin page.
How do I install Agent Replay in HOL Guard?
To install Agent Replay in HOL Guard, start with hol-guard plugin install sangloo/replay --apply. The complete step-by-step install guide for HOL Guard is on the HOL plugin page.
How do I install Agent Replay in Claude Code?
To install Agent Replay in Claude Code, start with /plugin marketplace add sangloo/agent-replay. The complete step-by-step install guide for Claude Code is on the HOL plugin page.
How do I install Agent Replay in Antigravity CLI?
To install Agent Replay in Antigravity CLI, start with npx [email protected] add sangloo/agent-replay. The complete step-by-step install guide for Antigravity CLI is on the HOL plugin page.
How is the Trust Score for Agent Replay computed?
Agent Replay has a HOL Trust Score of 69 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/sangloo%2Freplay/trust
Who publishes Agent Replay?
Agent Replay is published by sangloo 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