New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Verify Agent Context

by Luligu in Luligu/matterbridge

Verify which coding agent is running and that it loaded the shared Matterbridge instructions, rules and skills from AGENTS.md and .agents/.

Apache-2.0Auto-check passedAgent Workflows

Install Verify Agent Context

skills CLI
$ npx skills add Luligu/matterbridge --skill verify-agent-context -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Luligu/matterbridge verify-agent-context --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Luligu/matterbridge.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/verify-agent-context .claude/skills/verify-agent-context && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
verify-agent-context
GitHub stars
983
Token cost
~525 tokens
SKILL.md length
278 words
Files
1
Skills in repo
6
Repo updated
First seen
Licence
Apache-2.0

At a glance

Verify which coding agent is running and that it loaded the shared Matterbridge instructions, rules and skills from AGENTS.md and .agents/.

  • Works in 8 steps: First, report the absolute current… → State which agent you are (GitHub… → Confirm you have the shared instructions… → …
  • The user asks to check
  • Calls git
  • Debug the agent configuration

What it does

Verify Agent Context is an agent skill from Luligu/matterbridge. Verify which coding agent is running and that it loaded the shared Matterbridge instructions, rules and skills from AGENTS.md and .agents/. Use when the user asks to check, test or debug the agent configuration. v.1.0.4

Its SKILL.md is about 530 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Codebase knowledge for agents and Agent instruction files. It works with Git. The repository describes itself as: Matterbridge plugin manager for Matter. The licence is Apache-2.0.

When your agent uses it

  • The user asks to check
  • Debug the agent configuration

Example prompts

  • “/verify-agent-context”

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

  1. First, report the absolute current working directory and whether you are working in a linked Git worktree or a direct folder (the main…
  2. State which agent you are (GitHub Copilot, Codex, Claude Code or Gemini / Antigravity) and, if known, the model.
  3. Confirm you have the shared instructions from AGENTS.md in context. Quote its title line, including the version.
  4. List the rule files in .agents/rules/ and, for each, say whether its content is already in your context or only reachable on demand.
  5. List the skills you discovered from .agents/skills/ and from any tool-specific folder such as .claude/skills/ or .github/skills/.
  6. Read .agents/rules/testing.instructions.md and report the version at the end of its description frontmatter to prove the file is readable.
  7. Report the result as a markdown table with the columns Item, Status, Notes.
  8. Report the context size, including the number of instructions, rules, and skills currently loaded.

What it can do on your machine

Read from SKILL.md and the folder at commit 857fd9b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Verify Agent Context loads about 525 tokens when it runs. Until then it costs about 60 tokens; SKILL.md has 278 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~60
When it runs · the whole SKILL.md, loaded when a task matches
~525

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Luligu/matterbridge at commit 857fd9b, republished under its Apache-2.0 licence (© Luligu). 278 words, ~525 tokens.

Download SKILL.mdSave it as .claude/skills/verify-agent-context/SKILL.md (or your agent's skills folder).
name
verify-agent-context
description
Verify which coding agent is running and that it loaded the shared Matterbridge instructions, rules and skills from AGENTS.md and .agents/. Use when the user asks to check, test or debug the agent configuration. v.1.0.4

Agent configuration check

Run this check and reply with a short report. Do not modify any file.

  1. First, report the absolute current working directory and whether you are working in a linked Git worktree or a direct folder (the main checkout or a non-Git folder). Verify using git rev-parse --show-toplevel, git rev-parse --absolute-git-dir and git rev-parse --path-format=absolute --git-common-dir: different Git and common directories indicate a linked worktree; matching directories indicate the main checkout. If the folder is not a Git repository, report it as a direct non-Git folder. Report the current branch using git symbolic-ref --quiet --short HEAD; if HEAD is detached, report detached HEAD and the short commit ID from git rev-parse --short HEAD. For a non-Git folder, report the branch as not applicable. Include the repository root when it differs from the current directory, and make this location and branch information the first row of the report.
  2. State which agent you are (GitHub Copilot, Codex, Claude Code or Gemini / Antigravity) and, if known, the model.
  3. Confirm you have the shared instructions from AGENTS.md in context. Quote its title line, including the version.
  4. List the rule files in .agents/rules/ and, for each, say whether its content is already in your context or only reachable on demand.
  5. List the skills you discovered from .agents/skills/ and from any tool-specific folder such as .claude/skills/ or .github/skills/.
  6. Read .agents/rules/testing.instructions.md and report the version at the end of its description frontmatter to prove the file is readable.
  7. Report the result as a markdown table with the columns Item, Status, Notes.
  8. Report the context size, including the number of instructions, rules, and skills currently loaded.

© Luligu, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/verify-agent-context of Luligu/matterbridge.

Open the folder on GitHubat commit 857fd9b

Compare with similar skills

Verify Agent Context next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Verify Agent Context compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Verify Agent Context this skillLuligu/matterbridge983—~525Automated safety check: PassApache-2.0
Reconcile ContextApocrathia/home-assistant-config179—~931Automated safety check: PassNone
Neat-Freak Knowledge CloseoutKKKKhazix/khazix-skills21k—~1.9kAutomated safety check: PassMIT
Context Engineeringabashev/vfs-s31069 repos~2.6kAutomated safety check: NotesApache-2.0
Harness Evolution Feedback Looprevfactory/harness9.1k—~855Automated safety check: PassApache-2.0
Setup Matt Pocock Skillsywwynm/EverythingDone1449 repos~1.7kAutomated safety check: PassGPL-3.0

Similar skills

  • Reconcile Context

    Apocrathia/home-assistant-config

    Fix drift in Home Assistant Homelab agent context (AGENTS.md, CLAUDE.md, .agents/context/, rules, skills, agents) against the repo.

    179 GitHub stars~931 tokensUpdated 17 days ago
    Agent WorkflowsAuto-check passed

  • Neat-Freak Knowledge Closeout

    KKKKhazix/khazix-skills

    Brings project docs, agent rule files, authorized memory and leftover workspace files back in line with what the code and runtime actually do at the end of a work session.

    21k GitHub stars~1.9k tokensUpdated 7 days ago
    Agent WorkflowsAuto-check passed

  • Context Engineering

    abashev/vfs-s3

    Optimizes agent context setup. An agent skill from abashev/vfs-s3.

    106 GitHub starsUsed in 9 repos~2.6k tokens
    Agent WorkflowsAuto-check: notes

  • Harness Evolution Feedback Loop

    revfactory/harness

    Collects feedback on how an agent harness performed, generalizes it, and updates the harness agents, skills and orchestrator along with a change-history table.

    9.1k GitHub stars~855 tokensUpdated 10 days ago
    Agent WorkflowsAuto-check passed

  • Setup Matt Pocock Skills

    ywwynm/EverythingDone

    Sets up an Agent skills block in AGENTS.md/CLAUDE.md and docs/agents/ so the engineering skills know this repo's issue tracker (GitHub or local markdown), triage label vocabulary, and domain doc…

    144 GitHub starsUsed in 9 repos~1.7k tokens
    Agent WorkflowsAuto-check passed

  • Repo Context Ledger

    gviiisen/repo-context-ledger

    Record every behavior-changing feature addition, fix, and adjustment as durable, evidence-based repository knowledge, then use that ledger to continue accurately across AI windows, tools, Git…

    105 GitHub stars~2.8k tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed

More from Luligu/matterbridge

  • Matterjs PR Workflow

    Luligu/matterbridge

    Sync the matter.js fork, implement and test a fix or a new feature/enhancement, format, lint, commit, push, and open a PR against matter-js/matter.js.

    983 GitHub stars~2.4k tokensUpdated yesterday
    Auto-check passed

  • Verify npm Alignment

    Luligu/matterbridge

    Verify that matterbridge and all Matterbridge workspace packages are aligned on the npm latest and dev tags.

    983 GitHub stars~839 tokensUpdated yesterday
    Auto-check passed

  • Verify Server Endpoint Context

    Luligu/matterbridge

    Verify server message endpoint context, endpoint type narrowing, plugin forwarding order, command observable emission, and Matter 1.6.0 comments on validation and state updates.

    983 GitHub stars~5.1k tokensUpdated yesterday
    Auto-check passed

  • Verify Version Alignment

    Luligu/matterbridge

    Verify that package, Docker build, test utility helper, docs update JSON files, and Docker workflow tags match the expected root version rules.

    983 GitHub stars~1.7k tokensUpdated yesterday
    Auto-check passed

  • Verify Agent Context

    Luligu/matterbridge

    Verify which coding agent is running and that it loaded the shared Matterbridge instructions, rules and skills from AGENTS.md and .agents/.

    983 GitHub stars~195 tokensUpdated yesterday
    Auto-check passed

Works with

Categories

Questions about Verify Agent Context

What does Verify Agent Context do?

Verify which coding agent is running and that it loaded the shared Matterbridge instructions, rules and skills from AGENTS.md and .agents/. Verify Agent Context is an agent skill from Luligu/matterbridge.agents/.

When should I use Verify Agent Context?

Verify Agent Context fits situations like: the user asks to check; debug the agent configuration.

How do I install Verify Agent Context in Claude Code?

Run `npx skills add Luligu/matterbridge --skill verify-agent-context -a claude-code`. Or copy the skill folder (.agents/skills/verify-agent-context in Luligu/matterbridge) into .claude/skills/verify-agent-context in your project. Claude Code loads it when a task matches its description.

How do I install Verify Agent Context in Codex?

Run `npx skills add Luligu/matterbridge --skill verify-agent-context -a codex`. Or copy the skill folder (.agents/skills/verify-agent-context in Luligu/matterbridge) into .agents/skills/verify-agent-context in your project. Codex loads it when a task matches its description.

Can I use Verify Agent Context in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Luligu/matterbridge --skill verify-agent-context -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/verify-agent-context, .gemini/skills/verify-agent-context, .github/skills/verify-agent-context and .opencode/skills/verify-agent-context in your project.

What does Verify Agent Context need to run?

Going by SKILL.md and its folder, Verify Agent Context needs the command-line tools its instructions call (git).

Does Verify Agent Context access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Verify Agent Context safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Verify Agent Context use?

Verify Agent Context is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Verify Agent Context use?

About 525 tokens (SKILL.md is roughly 2.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Verify Agent Context?

Skills that share tags, products or a category with Verify Agent Context: Reconcile Context (Apocrathia/home-assistant-config, 179 stars), Neat-Freak Knowledge Closeout (KKKKhazix/khazix-skills, 21k stars), Context Engineering (abashev/vfs-s3, 106 stars) and Harness Evolution Feedback Loop (revfactory/harness, 9.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Verify Agent Context?

Luligu (a GitHub user) maintains it in Luligu/matterbridge, which has 983 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on October 7, 2026.

Source: Luligu/matterbridge on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.