> ## Documentation Index
> Fetch the complete documentation index at: https://docs.phylax.systems/llms.txt
> Use this file to discover all available pages before exploring further.

# Agentic PCL

> Use an AI coding agent to create, test, and deploy Credible Layer assertion projects with pcl

This guide shows you how to equip an AI coding agent to operate `pcl`, from creating an assertion project through deploying it with the Phylax platform.

Phylax publishes reusable instructions in the [agent-skills repository](https://github.com/phylaxsystems/agent-skills). These skills give compatible agents the project structure, safety boundaries, and `pcl` workflows needed to complete a task instead of relying on a large one-off prompt.

## Prerequisites

Before you begin, make sure you have:

* [`pcl` installed](./credible-install)
* An agent that supports the [Agent Skills format](https://agentskills.io), such as Codex or Claude Code
* A local protocol repository the agent can inspect and edit
* Clearly defined protocol invariants

For deployment, you also need a target chain, an RPC endpoint, and access to the protocol manager wallet.

Authenticate with the platform for your target network before starting the agent. See [How to Deploy Projects Through Agentic PCL](./agentic-pcl-deploy#1-authenticate-manually) for the Linea and Ethereum commands.

<Warning>
  An agent can edit code, create platform resources, and broadcast on-chain transactions. Review its plan and local changes before authorizing remote mutations. Require a successful dry run and explicit approval before any production deployment.
</Warning>

## Install the Phylax agent skills

Install the two PCL workflow skills from GitHub:

<CodeGroup>
  ```bash Codex theme={null}
  npx github:phylaxsystems/agent-skills#851cd274972efa6047393eaa61a935ed56f66b3b install pcl-assertion-workflow --agent codex
  npx github:phylaxsystems/agent-skills#851cd274972efa6047393eaa61a935ed56f66b3b install deploy-credible-assertions --agent codex
  ```

  ```bash Claude Code theme={null}
  npx github:phylaxsystems/agent-skills#851cd274972efa6047393eaa61a935ed56f66b3b install pcl-assertion-workflow --agent claude-code
  npx github:phylaxsystems/agent-skills#851cd274972efa6047393eaa61a935ed56f66b3b install deploy-credible-assertions --agent claude-code
  ```
</CodeGroup>

The commit pin ensures that both commands install the reviewed skill versions shown in this guide.

The [agent-skills repository](https://github.com/phylaxsystems/agent-skills) also includes focused skills for invariant design, assertion implementation, testing, backtesting, trigger optimization, and troubleshooting.

<Note>
  Restart your agent after installation if it does not discover the new skills in the current session.
</Note>

## Choose the workflow

| Goal                        | Skill                        | What the agent should do                                                                                                                     |
| --------------------------- | ---------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------- |
| Create an assertion project | `pcl-assertion-workflow`     | Inspect the protocol, create the assertion project structure, configure dependencies, and run local tests                                    |
| Deploy through the platform | `deploy-credible-assertions` | Use the existing authentication, check RPC configuration, create or resolve the platform project, create a release, and activate it on-chain |

Use the skill name in your request so the intended workflow is unambiguous.

## Start with a high-level prompt

You can describe the intended outcome and let the skills determine the required `pcl` workflow. Include the protocol, target environment, authoritative sources, release contents, and verification boundary.

For example:

```text theme={null}
Use the Agentic PCL skills to deploy an Aave V3 Horizon project end to end on
staging.

Find and verify the authoritative deployed contract addresses on-chain. Create
credible.toml using the latest reviewed Aave V3 assertions. Create the platform
project and release. Verify that the release is correct, then set the project
profile image from the specified official brand asset and deploy it.

RPC: <RPC URL or secure location>
Signer: <keystore or secure credential location>
Project branding: <official asset source and requested profile image>

Do not print, copy, or commit signing credentials. Ask for clarification if
sources conflict or any requested project metadata is ambiguous.
```

## Orient the agent with the installed CLI

Current versions of `pcl` expose machine-readable guidance for agents. Include this instruction in your prompt:

```text theme={null}
Before acting, inspect the installed pcl version, its machine-readable agent
guide, and the help for the relevant workflow command. Treat the installed CLI
as the source of truth. Prefer top-level workflow commands, structured JSON
output, and the next actions returned by pcl.
```

This prevents the agent from inventing flags or relying on a workflow from another `pcl` version.

## Keep a human in the approval loop

Authenticate with the target platform yourself before starting the deployment agent. Then give the agent autonomy for inspection, local file changes, builds, and tests. Require it to pause for:

* Any choice between staging and production
* Access to a signer or keystore
* Platform mutations
* On-chain broadcasts

Do not paste a private key into the conversation or commit it to the repository. Prefer a Foundry keystore and provide its password through a file outside the project.

<CardGroup cols={2}>
  <Card title="Create a Project with an Agent" icon="folder-plus" href="./agentic-pcl-create-project">
    Bootstrap and validate an assertion project locally
  </Card>

  <Card title="Deploy Projects Through Agentic PCL" icon="rocket" href="./agentic-pcl-deploy">
    Create a platform project and activate a release on-chain
  </Card>
</CardGroup>