About treeseed
treeseed is an agent skill for operating against a connected TreeSeed server. It guides agents to discover live capabilities and follow the server’s authorization, governance, and confirmation rules before acting.
Key features
- 01Discover current tools, resources, prompts, and schemas
- 02Check state before consequential changes
- 03Honor confirmation and concurrency checkpoints
- 04Follow durable resource links for asynchronous work
- 05Use TreeSeed library workflow for repository knowledge
Use cases
- 01Inspect available TreeSeed operations before a task
- 02Submit governed proposals or decisions
- 03Work with projects, agents, and assignments
- 04Retrieve repository-backed project knowledge
MCP support
The skill is designed for a connected TreeSeed MCP server. It directs agents to discover the server’s current tools, resources, templates, prompts, schemas, and annotations rather than assume a fixed interface.
Install
Copy the command and run it in a terminal.
npx skills add https:/After installing, type/treeseedin Claude Code to confirm it loaded.
Bundled files
References and scripts installed along with SKILL.md.
LICENSE.gitignoreAGENTS.mdcatalog-receipt.jsontreeseed.package.yaml.github/workflows/verify.ymlagents/openai.yamlreferences/knowledge.mdexecution.mdgovernance.mdmcp.mdprojects.mdscripts/verify.pytests/test_verify.pyDetails
From the project READMETreeSeed
Treat the connected TreeSeed server as the authority for identity, access, governance, scheduling, and receipts. Discover its current MCP tools, resources, templates, prompts, schemas, and capability annotations before choosing an operation. Do not rely on a remembered tool list or construct REST paths.
Operating boundary
- Act as the authenticated external principal. Do not claim project-agent identity unless an explicit, authorized project-agent chat operation returns that delegation.
- Read current state before a consequential mutation. Follow returned blockers, concurrency tokens, confirmation requests, resource links, and next actions.
- Use server-provided structured input and output schemas. Never place credentials, session material, private keys, or bearer tokens in tool arguments or model-visible content.
- Treat
input_requiredas a signed, exact-argument confirmation checkpoint. Ask the human when required; never alter, reuse, or synthesize confirmation state. - Follow durable
treeseed://resource links for asynchronous work. Use progress, cancellation, completion, and subscriptions when advertised instead of polling invented endpoints. - Do not invoke or emulate
save,stage, orreleaseuntil the server advertises their accepted governed operations. - For repository-backed project knowledge, use the
trsd libraryworkflow inreferences/knowledge.md; never assume an unbound virtual repository or asrc/contentlibrary root.
Choose the relevant guidance
- For questions, research, knowledge, or TreeDX projections, read references/knowledge.md.
- For proposals, decisions, estimates, reviews, or discussions, read references/governance.md.
- For teams, projects, repositories, or provider bindings, read references/projects.md.
- For agents, providers, capacity, plans, workdays, assignments, or explicit project-agent chat, read references/execution.md.
- For connection discovery, protocol behavior, errors, subscriptions, or confirmations, read references/mcp.md.
Distribution
Install and update the project-scoped skill with the pinned Vercel Labs Skills CLI version recorded by the consuming project:
npx [email protected] add treeseed-ai/skill --skill treeseed --agent codex --yes
npx [email protected] update treeseed --project --yes
The receipt pins published SDK and API evidence for this copy. Runtime discovery remains authoritative when a connected server advertises a newer compatible catalog. Installed files and skills-lock.json belong to the consuming project; this repository remains the source of releases.