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 swan-gtm/gtm-skills --skill clear-my-deskgit clone --depth 1 https://github.com/swan-gtm/gtm-skillsWrote 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/swan-gtm/gtm-skills/clear-my-desk)<a href="https://agentmods.dev/skills/swan-gtm/gtm-skills/clear-my-desk"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/clear-my-desk/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/swan-gtm/gtm-skills/clear-my-desk"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/clear-my-desk.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 27 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 72 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00041 | $0.01184 |
| Opus 5 | $0.00020 | $0.00592 |
| Sonnet 5 | $0.00008 | $0.00237 |
| Haiku 4.5 | $0.00004 | $0.00118 |
Grade A, and why
clear-my-desk 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 9d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instructions
State check. This skill assumes the caller is the user whose desk is being cleared and that the org actually generates review items and sequence approvals — i.e. at least one play or radar is wired up producing tasks. Run swan-search-user-tasks filtered to the caller as the first probe. If nothing comes back across statuses, the desk is empty because no plays are producing work yet, not because the user is on top of it — tell the user and recommend wiring up a radar or play before this skill becomes useful.
What this skill does
The user has a backlog and wants to clear it in one pass without reading every item. Triage in slices, summarize as you go, never load the whole desk into context. By the time the agent has scanned a few high-signal slices, it should know what's bulk-approvable and what needs attention.
Step 1 — Scan high-priority items first
Call swan-search-user-tasks filtered to the caller, status: PENDING, ordered by priority/recency, page size ≤ 20. Read the structural preview the agent gets back — it shows the shape (taskType, companyId, age, priority) for the first 20 items.
For each item in this slice, classify in one pass:
| Bucket | Criteria | Per-item record |
|---|---|---|
| Act today | High priority, named target account, fresh signal | Title + one-line context |
| Bulk approve | Outreach sequence approval, shared template, looks safe | Group key (template + sender) |
| Acknowledge | Stale informational alerts, low-priority FYIs | Group key (taskType + age bucket) |
| Stop / investigate | Auto-approved sequence with a red flag | Title + the concern |
| Worth a look | Open-ended suggestion needing user judgment | Title + impact score 1-5 |
Keep a running tally as a short JSON in your head — one entry per item, max one line per item. Drop the raw task objects after classification.
Step 2 — Decide whether to keep going
After the first slice of 20:
- If at least 8 items hit "Act today" or "Stop / investigate" → the desk is hot. Stop scanning, report, let the user act. Don't drown them in more items.
- If the slice is mostly "Acknowledge" with very little action → fetch the next page (20 more), same classification pass. Repeat up to ~60 items total.
- If the slice is mostly empty / boring → the desk is in good shape; report briefly and stop.
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.
- 9d ago First seen · 77 lines · 41 tokens per session scan A 294686bcddef
clear-my-desk is a skill published in the GitHub repository swan-gtm/gtm-skills (150 stars, last pushed 2d ago), licensed MIT. It adds 41 tokens to every session and 1,184 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
meeting-type-management
Manages Chili Piper team meeting types and their email/SMS reminders — list, inspect, create, update, delete — with dry-run planning, guest-visible-field safety (inviteTitle/inviteDescription vs internal description), and reminder attach/detach.
scheduling-link-management
Lists, creates, updates, and deletes Chili Piper scheduling links across all four admin link types (round-robin, admin one-on-one, group, ownership) plus personal-link auditing — with dry-run planning and delete safety (deletion instantly breaks the link's booking URL).
availability-inspector
Checks why a rep or team is showing no available slots — diagnoses calendar connectivity, working hours, meeting limits, and distribution membership to find the specific blocker.
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…