Skip to content

For the complete documentation index, see llms.txt.

Supported agents

An agent can use your hub’s instructions without sending traces to PIG. Plugin distribution, native trace collection, and repository analysis have different support boundaries.

AgentGenerated instruction distributionNative trace collection
Claude CodeClaude plugin and marketplaceYes, through the opt-in pig runtime and generated hooks
CodexCodex plugin and marketplaceYes, through the opt-in pig runtime and generated hooks
CursorCursor plugin and marketplaceDesktop Agent sessions, through the opt-in pig runtime and generated hooks, with analyzer 0.3.3 or later
Gemini CLIGemini extensionNot currently supported
Claude DesktopNot a separate compiler targetIts native traces can be discovered by the Claude collector on the same host

The targets entries in hub.yaml are claude, codex, cursor, and gemini. Include only the targets you distribute, or keep all four from pig init.

Trace collection defaults to off. When enabled, the toolchain adds runtime files and collection hooks only to the literal pig plugin for Claude, Codex, and Cursor. Claude Code’s hook also attempts local Claude Desktop collection; this does not create a separate collection schedule inside Claude Desktop. The default enrollment policy includes Cursor once your analyzer reports Cursor support, which analyzer releases 0.3.3 and later do. See host enrollment and its Cursor collection limits.

Claude Code and Codex agents in cloud sandboxes, such as Claude Tag, can also send native traces. They enroll each execution with a cloud integration grant and need no pig plugin from your hub. See Capture traces from cloud agents.

The hub stores assets independently from plugins. A plugin’s includes references choose which assets it distributes. Asset metadata determines how each target receives them.

AssetDefault behaviorAuthoring guidance
Skills in assets/skills/<id>/SKILL.mdAgent Skills on all four targetsPrefer this format for shared, task-oriented guidance; include supporting files in the skill directory
MCP configurations in assets/mcps/Native MCP configuration on all four targetsVerify the server’s transport, command, credentials, and host-specific settings on every target you use
Rules in assets/rules/Unsupported until declaredAdd explicit target support; do not assume a repository rule applies identically across agents
Agent definitions in assets/agents/Unsupported until declaredDeclare native support or a supported conversion for each intended target
Commands in assets/commands/Unsupported until declaredReview the host’s invocation and file format
Hooks in assets/hooks/Unsupported until declaredReview event names, commands, and the host’s execution environment

Skills use agent-skill mode by default, including in Cursor. They do not become always-on Cursor rules. An explicit Cursor rule uses .mdc output when its support declaration selects that behavior.

Place metadata for a directory asset in its asset.yaml. For a file asset, use a sibling named <id>.asset.yaml. For example, a Cursor-only rule at assets/rules/docs-style.md can use:

assets/rules/docs-style.asset.yaml
support:
cursor:
mode: native

Other targets retain the rule’s default unsupported status. To record a deliberate exclusion for a particular target, use mode: unsupported with a reason:

support:
cursor:
mode: native
codex:
mode: unsupported
reason: This rule depends on Cursor file matching.

Support declarations describe the intended output; they do not make arbitrary host formats portable. Use pig verify to check the selected conversions, then install and exercise the asset on each target. A supported Markdown agent definition can be native on Claude and converted to an Agent Skill on Codex. That conversion does not preserve a separate subagent’s execution or model-selection behavior.

CapabilityGitHubGitLab
Author and review hub sourceYesYes
Validate and publish generated releasesReusable GitHub ActionsGitLab CI template
Distribute generated pluginsSupported, subject to the agent’s access and import requirementsSupported by the toolchain; the agent must support the chosen import route
Bind repositories for trace analysis and finding issuesYesNot currently supported

Cursor’s documented team marketplace import flow uses GitHub. A generated GitLab marketplace and working Git credentials do not prove that a particular Cursor importer accepts it. Pilot that path before rolling it out. See installation by agent.

The current analyzer reads the GitHub repositories an administrator selects in PIG Settings. It uses their repository IDs to associate traces with repositories and manage findings. Publishing an Instruction Hub on GitLab does not by itself add GitLab repository analysis. Choose the hub’s Git provider separately from the repositories your analyzer can currently process.

Pilot each agent and plugin combination before you roll it out. For Acme, start with one writer and one developer using the docs and dev plugins. Run these checks on each agent during the pilot, and again after an asset’s target support changes:

CheckConfirm that
Plugin installationThe agent lists the installed plugin.
Skill loadingThe agent loads the intended skill and its supporting files.
Task behaviorThe agent follows the skill on a representative task.
Collection and analysisWhen trace collection is enabled, the host is enrolled, a trace is stored, and an analysis run completes. The deployment guide covers these operator checks.

For the native session files the collector reads on each host, see Trace object and sources.