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/yugmarwaha/todoist-weekly-review-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/yugmarwaha/todoist-weekly-review-mcp/todoist-weekly-review)<a href="https://agentmods.dev/commands/yugmarwaha/todoist-weekly-review-mcp/todoist-weekly-review"><img src="https://agentmods.dev/badge/commands/yugmarwaha/todoist-weekly-review-mcp/todoist-weekly-review/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/yugmarwaha/todoist-weekly-review-mcp/todoist-weekly-review"><img src="https://agentmods.dev/badge/commands/yugmarwaha/todoist-weekly-review-mcp/todoist-weekly-review.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 | $0.00644 |
| Opus 5 | $0.00008 | $0.00322 |
| Sonnet 5 | $0.00003 | $0.00129 |
| Haiku 4.5 | $0.00002 | $0.00064 |
Grade A, and why
todoist-weekly-review 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run my Todoist weekly review. Follow this exact process:
Overdue pass
- Call the
get_overdue_taskstool. If it errors about a missing token, show the user the error's setup instructions and stop. - If there are no overdue tasks, say so and move on to the stale pass below.
- Present the tasks as a numbered table: content, project, days overdue, times rescheduled, priority (translate the API value for display: API 4 = P1/highest, API 1 = P4/normal).
- For EACH task, propose exactly one fix with a one-line reason: reschedule to a concrete date, change priority, retire it (complete, or move to "Someday/Maybe" and clear its date), or — if the task's text is really a whole multi-step project (a Hidden Project, e.g. "plan trip") — split it into 2-20 concrete sub-tasks and show the exact list. Chronic offenders (high daysOverdue + high timesRescheduled) should usually be retired, not rescheduled again. For recurring tasks (isRecurring: true), remember that completing advances the recurrence instead of retiring — say so when relevant.
- Ask the user to approve or veto each item by number, in plain language. WAIT for their reply. Do not call any write tool yet.
Stale pass
- Call the
get_stale_taskstool (default threshold — omitminDaysSinceUpdateunless the user asked for a different window). If there are no stale tasks, say so and move on. - Present the tasks as a second numbered table: content, project, days since activity, age.
- For EACH task, propose exactly one fix with a one-line reason: retire it (complete, or move to "Someday/Maybe"), reword it into a concrete next action, reschedule it to give it a real date, or — same Hidden Project judgment as above — split it into 2-20 concrete sub-tasks and show the exact list.
- Ask the user to approve or veto each item by number, in plain language. WAIT for their reply. Do not call any write tool yet.
Apply and confirm
- Once the user has responded to both passes, call
apply_changeswith ONLY the approved items from both passes — never include anything the user vetoed or didn't explicitly confirm. You may send all survivors in oneapply_changescall or split overdue and stale survivors into two calls; either way, never call it before the user has explicitly approved every item you include. - Report the per-item results, then call
get_overdue_tasksandget_stale_tasksagain and summarize what changed and what remains.
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 · 47 lines · 15 tokens per session scan A f00575217611
todoist-weekly-review is a command published in the GitHub repository yugmarwaha/todoist-weekly-review-mcp (0 stars, last pushed 23d ago), licensed MIT. It adds 15 tokens to every session and 644 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 2026-09-01.
Other commands, from other repositories
standup
Quick daily standup from today's Claude Code sessions — grouped by project, with cost and errors.
fire-todos
Capture, list, and manage todos during work sessions.
gsd:resume-work
Resume work from previous session with full context restoration.
todo.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
standup
A command that creates a daily stand-up report by summarizing recent work, planned tasks, calendar events, and blockers.
ops
Weekly operations loop — triage the inquiry inbox, advance the CRM pipeline, sweep open PRs across repos, and surface the content plan. Loads the ops skill.