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 skills add MarimerLLC/rockbot --skill mcpserver.todoappgit clone --depth 1 https://github.com/MarimerLLC/rockbotWrote 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/skills/marimerllc/rockbot/mcpserver.todoapp)<a href="https://agentmods.dev/skills/marimerllc/rockbot/mcpserver.todoapp"><img src="https://agentmods.dev/badge/skills/marimerllc/rockbot/mcpserver.todoapp/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/skills/marimerllc/rockbot/mcpserver.todoapp"><img src="https://agentmods.dev/badge/skills/marimerllc/rockbot/mcpserver.todoapp.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 | $0.00000 | $0.01583 |
| Opus 5.5 | $0.00000 | $0.00633 |
| Sonnet 5.5 | $0.00000 | $0.00317 |
| Haiku 4.5 | $0.00000 | $0.00158 |
Grade A, and why
McpServer.TodoApp 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 17d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Todo MCP Server — Skill Document
Overview
A persistent to-do list with recurring tasks, an activity log per task, and undo for deletes and completions. Every call is strict and every failure is a real tool error, so a call that "succeeds" really did what it says.
Source of truth: this document lives in the RockBot repo at
src/McpServer.TodoApp/SKILL.md. Edit it there and re-publish it withupdate_skill, so the repo and the aggregator stay in sync.
Conventions (read these first)
- Dates are
YYYY-MM-DD, date-only, with no time zone.list_completedfilters (completed_after/completed_before) take ISO datetimes. - Everything is snake_case, in and out:
due_date,series_id,month_anchor, and so on. Enum values are lowercase:biannual, notbiAnnual. - Unknown arguments are rejected. A misspelled or unsupported key fails with an error naming it and listing the valid ones; it is never silently ignored. An enum value outside its allowed list (e.g.
recurrence: "fortnightly") fails the same way. - Errors are
isError: trueresults. If a call didn't error, it did what it says. - Ids are GUIDs. Every occurrence of a recurring task has its own id, and occurrences share a
series_id. due_beforeanddue_afterare exclusive. To get tasks due on or before 2026-10-31, passdue_before: "2026-11-01".
Tools
| Tool | Use it to |
|---|---|
list_tasks |
Overview of active tasks, sorted by due date. Use compact: true for id/title/due_date/recurrence only, and query to search title and description. Notes appear only as note_count + last_note. |
get_task |
Full detail for one id, including all notes. Returns { status, task }; status is active, completed or deleted. |
add_task |
Create a task. Optional recurrence, recurrence_until, recurrence_count, month_anchor, description. |
update_task |
Change fields on an active task. The id is always preserved. Can change recurrence, the series limits and month_anchor. |
add_task_note |
Append a status or observation to a task's log. Use this, not description, for progress updates. |
complete_task |
Complete a task. Returns { completed, next, series_ended }. Pass stop_recurrence: true to end a series. |
uncomplete_task |
Undo a completion. Removes the auto-created next occurrence if it is untouched. |
delete_task |
Soft-delete a task (recoverable for 30 days). |
restore_task / list_deleted |
Bring back a deleted task / see what can be restored. |
list_completed |
Completed history, most recent first. Supports query, compact and sort. |
What ships with it
15 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- appsettings.json 120 B
- Dockerfile 1.3 KB
- McpServer.TodoApp.csproj 467 B
- Models/MonthAnchor.cs 465 B
- Models/RecurrenceType.cs 126 B
- Models/SortOrders.cs 548 B
- Models/TodoItem.cs 1.2 KB
- Program.cs 548 B
- README.md 7.8 KB
- ServerInstructions.cs 951 B
- Services/Recurrence.cs 2.0 KB
- Services/TodoRepository.cs 4.1 KB
- StrictArguments.cs 4.8 KB
- Tools/TodoTools.cs 33 KB
- Tools/ToolJson.cs 1.1 KB
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.
- 17d ago First seen · 91 lines · 0 tokens per session scan A 0600c0a9b63a
McpServer.TodoApp is a skill published in the GitHub repository MarimerLLC/rockbot (34 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,583 tokens. 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 2026-10-08.
Other skills, from other repositories
stale-sweep
Sweep the googleapis/mcp-toolbox repo for issues and PRs with no real activity in N days (default 60), sort each by whose silence it is (the author's, ours, or nobody's), and draft the nudge or close comment. Use whenever a maintainer asks for a stale sweep, backlog cleanup, or an SLO check, e.g. "stale sweep", "find…
linear-tickets
Create or update high-quality Linear tickets while preserving the originating report, diagnostic links, attachments, and reporter/requester attribution. Read this whenever someone asks to create, recreate, or update a Linear issue.
omh-research-department
This is a Hermes-native research-department workflow skill.
devloop
Goal-driven development loop — define objective, write rules with key-results, verify visually, sync to issue tracker.
omh-agent-board
This is a Hermes-native agent-board workflow skill.
company-employee
The protocol every employee of a PenguinHarness organization follows — read the handbook first, act on [orgtrigger] work runs, schedule tickets from the desk session and do the work in ticket sessions, block instead of idling, ask the board in the all-hands channel before anything heavy, costly, irreversible or…