Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/Onplana/onplana-mcp-serverWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/onplana/onplana-mcp-server/onplana-connect)<a href="https://agentmods.dev/commands/onplana/onplana-mcp-server/onplana-connect"><img src="https://agentmods.dev/badge/commands/onplana/onplana-mcp-server/onplana-connect/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/onplana/onplana-mcp-server/onplana-connect"><img src="https://agentmods.dev/badge/commands/onplana/onplana-mcp-server/onplana-connect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00015 | $0.00520 |
| Opus 5 | $0.00008 | $0.00260 |
| Sonnet 5 | $0.00003 | $0.00104 |
| Haiku 4.5 | $0.00002 | $0.00052 |
Grade A, and why
onplana-connect scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Connect this Claude Code session to Onplana's MCP server and confirm the connection before reporting success.
Why this is a command and not part of the manifest
A Claude Code plugin declares MCP servers in the stdio form (command, args,
env). Onplana's server is remote and OAuth-authenticated at
https://mcp.onplana.com/mcp, so it is attached at runtime instead. Anthropic's
own listed integrations for hosted products do the same thing.
Steps
-
Add the server. Prefer
--scope userso it follows the person rather than one checkout, unless they say they want it only in this project:claude mcp add --transport http --scope user onplana https://mcp.onplana.com/mcp -
Authenticate. Run
/mcp, choose onplana, and complete the browser sign-in. The token is issued to the Onplana organization the person signs in as, and it lasts 90 days. -
Verify rather than assume. Call
whoamiand report the account and organization it returns. If the tool list is empty or the call fails, the connection is not usable yet, so say so plainly instead of continuing.
What they get
Roughly 265 tools, scoped to the signed-in organization and filtered by that person's own role and plan. Reads and writes both go through the same permission checks the web app uses, and every write is audited.
Two skills ship with this plugin:
- onplana:onplana-project-planner turns a goal or a brief into an executable plan: a plan document attached to the project, then a task tree with dates, dependencies, owners and test cases.
- onplana:onplana-autonomous-agent runs an existing plan: claim a task, work it, record progress and evidence, resolve or hand it back, then take the next one.
Suggest the planner skill when they want a plan built, and the autonomous skill when a plan already exists and they want it executed.
If they do not have an account
Onplana has a free tier and the MCP server is available on every plan, including free. Point them at https://onplana.com and continue once they can sign in.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 54 lines · 15 tokens per session scan A 237bec575c5f
onplana-connect is a command published in the GitHub repository Onplana/onplana-mcp-server (4 stars, last pushed 14d ago), licensed MIT. It adds 15 tokens to every session and 520 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
backlog-from-demo
Turn a recorded product demo into a prioritized backlog with timestamped evidence.
staff-event
Build a complete event staffing plan (configured-market match, W-2 rates, tier-based lead time, compliance) and prepare a buyer-submitted quote form.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.