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 ZeeshanAdilButt/goalslot-mcp --skill goalslot-plan-my-weekgit clone --depth 1 https://github.com/ZeeshanAdilButt/goalslot-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/skills/zeeshanadilbutt/goalslot-mcp/goalslot-plan-my-week)<a href="https://agentmods.dev/skills/zeeshanadilbutt/goalslot-mcp/goalslot-plan-my-week"><img src="https://agentmods.dev/badge/skills/zeeshanadilbutt/goalslot-mcp/goalslot-plan-my-week/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/zeeshanadilbutt/goalslot-mcp/goalslot-plan-my-week"><img src="https://agentmods.dev/badge/skills/zeeshanadilbutt/goalslot-mcp/goalslot-plan-my-week.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 | $0.00071 | $0.00948 |
| Opus 5 | $0.00036 | $0.00474 |
| Sonnet 5 | $0.00014 | $0.00190 |
| Haiku 4.5 | $0.00007 | $0.00095 |
Grade A, and why
goalslot-plan-my-week 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan a week on GoalSlot
The one thing to get right
The GoalSlot schedule is a repeating weekly template, not a calendar. A block on Tuesday 09:00 to 12:00 happens every Tuesday, forever, until someone removes it. There is no way to schedule something for one specific date.
Say this back to the user before you write anything. "I will add Deep Work on Tuesday mornings" means every Tuesday, and people routinely expect it to mean next Tuesday only.
Sequence
goalslot_get_context. You needtoday,timezone,categories[].value, andplan.limits.scheduleBlocksagainstplan.usage.scheduleBlocks.goalslot_list_goalswithstatus: "ACTIVE". For each goal compute the gap:targetHours - loggedHours, and if it has adeadline, the weekly hours needed to close that gap before it.goalslot_get_schedule. This is what already exists. Readdays[].blocksand note the free windows.goalslot_get_reportwithview: "summary",groupBy: "goal",preset: "last_week". This is where the hours actually went, which is usually not where the template said they would.goalslot_get_reportwithview: "schedule"over the last two or three weeks. This separates two problems that look identical from the outside:- a goal with no block allocated: the fix is to add time.
- a goal with a block allocated and near 0 percent logged against it: the fix is not more blocks. Ask what got in the way.
- Propose the whole week to the user in one message, as a table of day, time, title, goal. Do not write yet.
- Dry run every block:
goalslot_manage_schedule_blockwithaction: "create"anddryRun: true. This validates shape and shows the durations. - Only after the user says yes, call it again for each block without
dryRun.
Rules
- Never write before the user has seen the whole plan. One block at a time as you think of it is how people end up with a schedule they did not agree to.
- Stop one short of the plan limit.
get_contexttells you the ceiling. If the user is on FREE with 5 blocks and already has 4, you can add one. Say that rather than proposing six and erroring intoPLAN_LIMITon the second. - On
SCHEDULE_CONFLICT, do not delete anything. Re-read that day withgoalslot_get_schedule, find the next free window, and propose the shift to the user. Removing the incumbent block to make room is a decision only they get to make. categoryis a value string, fromget_context.categories[].value, likeDEEP_WORK. Not the display name, not an id. A wrong value does not error; it silently produces an uncategorized block.dayOfWeekis Sunday-first: 0 is Sunday, 1 is Monday, 6 is Saturday. The weekly reports are Monday-first. These are different orderings and mixing them puts blocks on the wrong day.- Blocks cannot cross midnight. A 22:00 to 01:00 session is two blocks.
- Optionally create one task per block with
goalslot_create_task, linkingscheduleBlockIdandgoalId. Do this only if the user asked for tasks; otherwise it is clutter.
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 · 42 lines · 71 tokens per session scan A d91d23000c53
goalslot-plan-my-week is a skill published in the GitHub repository ZeeshanAdilButt/goalslot-mcp (0 stars, last pushed 18d ago), licensed MIT. It adds 71 tokens to every session and 948 once invoked, about $0.0004 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 skills, from other repositories
clockify-automate
Turn on agent-mediated Clockify tracking: if .clockify/config.yml is missing, run minimal clockify-init first, then forge wizard (GitHub) + Cursor Plan/Debug platforms + runaway wizard, ensure project/tasks, write Cursor rules, and when runaway is enabled install Clockify-owned runaway hooks. Use when the user wants…
clockify-automate-disable
Temporarily pause agent-mediated Clockify tracking without wiping settings: remove the clockify Cursor rule and Clockify-owned runaway hooks, set entry.automated.enabled false and platforms.cursor.enabled false, but keep forge, settings.onstart, triggers, settings.runaway prefs, and modes. Distinct from…
clockify-unautomate
Full rollback of agent-mediated Clockify tracking: remove the clockify Cursor rule and Clockify-owned hooks, and reset entry.automated in .clockify/config.yml to init/example defaults (all forge..enabled false, empty triggers, platforms.cursor off, modes cleared). Does not change plugin, scope, timer, or manual. Use…
clockify-automate-enable
Resume agent-mediated Clockify tracking after clockify-automate-disable: set entry.automated.enabled true, restore platforms.cursor.enabled from preserved modes, rewrite .cursor/rules/clockify.mdc, and reinstall runaway hooks when settings.runaway.enabled is still true. Skips forge/Cursor/runaway wizards unless…
clockify-start-timer
Start a Clockify running timer for the current repo. Use when the user asks to start tracking, clock in, or start a timer on an issue. Honors the timer block in .clockify/config.yml. Warns before stopping a different running timer. Optional backdated start.
clockify-stop-timer
Stop the currently running Clockify timer. Use when the user asks to stop tracking, clock out, or finish an issue/PR in this session. Honors timer rounding and overlap. Does not summarize the whole day.