agentleFS
glifxyzglifxyz/glif-mcp-server/AGENTS.md

glif-mcp-server

AGENTS.md213 starsChanged 37 days agoMITView on GitHub

This repo is public. Everything in it is published: files, history, commit messages, PR titles, PR descriptions and comments. Plugin directories, MCP registries, skill crawlers and security scanners copy it, and reviewers at Anthropic and OpenAI read all of it. Every file here is user-facing documentation, a manifest or a skill. Before you add a sentence, ask: would we be happy to see this quoted on a directory listing? Keep out of this repo, including commits and PRs: Internal notes…

  • Reads credentials

The file

We split this AGENTS.md into the rules it gives an agent

5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Distinctive:

    Every file here is user-facing documentation, a manifest or a skill.

    line 7
  2. Distinctive:

    Keep out of this repo, including commits and PRs:

    line 9
  3. Distinctive:

    Read the full diff and your commit message against the list above.

    line 25
  4. Very specific:

    Never commit ignored files such as .env or key.pem.

    line 26
  5. Distinctive:

    Run the checks CI runs:

    line 27

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
AGENTS.md

Glif MCP server, plugin and skills

This repo is public. Everything in it is published: files, history, commit messages, PR titles, PR descriptions and comments. Plugin directories, MCP registries, skill crawlers and security scanners copy it, and reviewers at Anthropic and OpenAI read all of it.

Write only for users

Every file here is user-facing documentation, a manifest or a skill. Before you add a sentence, ask: would we be happy to see this quoted on a directory listing?

Keep out of this repo, including commits and PRs:

  • names, branches or paths of private repos, such as glif-graph
  • plans, roadmaps, effort estimates, launch timing and unreleased features or arguments
  • store submission strategy, review notes, test cases, reviewer accounts and comments on store policies
  • internal pricing figures, costs, margins, metrics, analytics and user or customer data
  • staff names and personal emails (use contact@glif.xyz), internal hostnames, dev or staging URLs
  • secrets, API keys, tokens, private keys and .env contents
  • dated local-testing diaries like "checked locally on..." and candid opinions about other companies

Internal notes belong in glif-graph's docs/store-submissions.md, which is private.

Describe only what production does today. Skills may tell agents that video uses more credits than images, but they link to https://glif.app/pricing rather than quoting numbers.

Before you commit

  • Read the full diff and your commit message against the list above.
  • Never commit ignored files such as .env or key.pem. Stage files by name.
  • Run the checks CI runs:
claude plugin validate --strict .
for skill in skills/*/; do uvx --from skills-ref agentskills validate "$skill"; done

Repo facts

  • The hosted server is https://glif.app/api/mcp. Every manifest names it glif.
  • .claude-plugin/ is the Claude plugin and marketplace. Root plugin.json and mcp.json are the Agent Plugins format. gemini-extension.json is Gemini CLI. server.json is the MCP Registry.
  • Bump version in .claude-plugin/plugin.json, plugin.json and gemini-extension.json together. CI fails if they differ.
  • Publish server.json by bumping its version and tagging v<version>.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.