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.
npx agentmods add commands/dsudomoin/weeek-mcp/weeek-setupgit clone --depth 1 https://github.com/dsudomoin/weeek-mcpWrote 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/dsudomoin/weeek-mcp/weeek-setup)<a href="https://agentmods.dev/commands/dsudomoin/weeek-mcp/weeek-setup"><img src="https://agentmods.dev/badge/commands/dsudomoin/weeek-mcp/weeek-setup.svg" alt="Measured on agentmods" 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 | $0.00639 |
| Opus 5 | $0.00008 | $0.00319 |
| Sonnet 5 | $0.00003 | $0.00128 |
| Haiku 4.5 | $0.00002 | $0.00064 |
Grade A, and why
weeek-setup 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 5d 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.
What it actually says
The user wants to set the Weeek MCP server up without leaving a token in a configuration file.
The server needs one thing: a Weeek API token. A wizard asks for it, so all you have to do is walk the user through running it.
Do not ask the user for their token, and do not run the wizard yourself. It reads the token from the terminal without echoing it, which only works when the user runs it, and it refuses outright when its input is a pipe. A token you receive in this conversation is a token written into the transcript, which is the one outcome the keychain exists to prevent. Tell them to run this in their own terminal:
weeek-mcp init
If the server is not on their PATH — which is the case when their client
launches it through npx rather than from a global install — the same wizard
runs with:
npx -y @dsudomoin/weeek-mcp init
Explain what will happen, so nothing is a surprise:
- It asks for the token, and nothing is shown as they type.
- It checks the token against Weeek before storing anything. If Weeek rejects it, nothing is written anywhere.
- It says who the token belongs to, so they can tell a wrong account from a wrong token.
- It stores the token and names the place — the macOS Keychain, the Windows Credential Manager, the Secret Service, or a file readable only by them when the machine has no usable keychain. Ask them to read that line back: it is the difference between a token that survives a reboot and one that does not.
- It says to restart the client. That part is not optional: the token is read once, when the server starts.
Tokens are created in Weeek under Settings → API.
Once they say it finished, and once the client has been restarted, verify it by
calling weeek_context. It should return their name, the workspace and its
projects. If it fails:
- "WEEEK_API_TOKEN is not set and no token is stored" means the wizard did not complete, or it ran against a different installation than the one the MCP client launches. Ask them to read out what it printed.
- A 401 from Weeek means the token was revoked after it was stored. Run the wizard again.
- The server is not listed at all means the MCP client has not been restarted since the server was added.
If the user would rather not store anything, the server also reads
WEEEK_API_TOKEN from the environment, and that takes priority over anything
stored on the machine. That is the right path for containers, for CI, and for
Codex, which replaces the environment of every server it launches.
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.
- 5d ago First seen · 62 lines · 15 tokens per session scan A 78dd2978d510
weeek-setup is a command published in the GitHub repository dsudomoin/weeek-mcp (0 stars, last pushed 5d ago), licensed MIT. It adds 15 tokens to every session and 639 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
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.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.