CodePlans / AI agents

The system of record your coding agents read — and write

CodePlans records what shipped, where and why. Connect a coding agent over MCP (75 tools) and the record builds itself as the work happens.

AI agents guideMCP server spec
📖

Agents read the map

Before touching an asset, an agent pulls its history, open debt, dependencies, active specs and delivery coverage. get_asset_record separates current intent from delivered capabilities, and search finds any product, asset, plan, task, work item, spec or release by text.

✍️

Agents write the record

As plans complete, agents mark tasks done, update branch and PR status, file the debt they discover, and record a design note on each asset they changed, with an agent badge.

💬

Agents join the loop

Agents request reviews, read and add comments, and start a session with get_my_work: "what's waiting on me?". There is deliberately no tool to approve a review.

📝

AI drafts, humans decide

With an Anthropic API key configured, CodePlans drafts release notes and design notes from delivered work. Drafts always land in an editor; nothing is auto-published.

Connect

Add CodePlans to your agent

Generate an API key in Settings → API Keys. Snippets are included for Claude Code, Claude Desktop, Cursor, Codex CLI, GitHub Copilot and Antigravity. Keys act as your user, so access rules apply unchanged.

# Connect Claude Code to your CodePlans instance
claude mcp add --transport http codeplans http://localhost:3000/api/mcp/mcp \
  --header "Authorization: Bearer cpk_your_key"

See the AI agents guide for the 75-tool catalog and the recommended agent workflows.

Agent skills

Teach your agent the workflows

CodePlans publishes agent skills: short instructions that turn its workflows into one-line requests like log this in CodePlans. In Claude Code, the plugin installs them and connects the MCP server; it asks for your CodePlans URL and an API key.

# Claude Code: skills and the MCP connection
/plugin marketplace add SylonZero/CodePlans
/plugin install codeplans@codeplans

# Any agent (Codex, Cursor, Copilot…): skills only
npx skills add SylonZero/CodePlans

/codeplans-context

Before a change: owners, dependents, history, design notes, specs, debt and open issues for the assets involved.

/codeplans-log

After a session: the plan, tasks, branch and PR status, and the debt and follow-ups found along the way.

/codeplans-spec

Read, write, revise or supersede a spec and link it to the assets, work items and plans it governs.

/codeplans-close-plan

Complete a plan, record design notes on the changed assets, and graduate delivered features into the asset record.

/codeplans-release

Create a release, attach its plans, stamp asset versions and ship it.

/codeplans-model, /codeplans-capture, /codeplans-my-work

Model a repo as assets, import an existing docs folder, and see what's waiting on you.

See the agent skills guide. Skills that write ask before anything people would want to check: completing a plan, shipping a release, or writing a proposed model.

← PreviousMy Work