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 skills/servosity/msp-skills/autotasknpx skills add Servosity/msp-skills --skill autotaskgit clone --depth 1 https://github.com/Servosity/msp-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/servosity/msp-skills/autotask)<a href="https://agentmods.dev/skills/servosity/msp-skills/autotask"><img src="https://agentmods.dev/badge/skills/servosity/msp-skills/autotask.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 | $0.00096 | $0.11802 |
| Opus 5 | $0.00048 | $0.05901 |
| Sonnet 5 | $0.00019 | $0.02360 |
| Haiku 4.5 | $0.00010 | $0.01180 |
Grade A, and why
autotask scanned grade A with 1 finding 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 3d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
bash <(curl -fsSL https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/autotask/install.sh) The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What ships with it
60 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.
- .claude-plugin/plugin.json 601 B
- AGENTS.md 2.3 KB
- CHANGELOG.md 3.7 KB
- cli/.golangci.yml 147 B
- cli/cmd/autotask-cli/main.go 353 B
- cli/cmd/autotask-mcp/main.go 2.1 KB
- cli/go.mod 966 B
- cli/go.sum 7.0 KB
- cli/internal/cache/cache.go 1.7 KB
- cli/internal/cli/account_brief.go 6.4 KB
- cli/internal/cli/agent_context.go 7.2 KB
- cli/internal/cli/analytics.go 5.0 KB
- cli/internal/cli/api_discovery.go 3.6 KB
- cli/internal/cli/appointments_create-entity.go 8.7 KB
- cli/internal/cli/appointments_delete-entity.go 6.5 KB
- cli/internal/cli/appointments_patch-entity.go 8.7 KB
- cli/internal/cli/appointments_query-count.go 7.8 KB
- cli/internal/cli/appointments_query-entity-information.go 3.0 KB
- cli/internal/cli/appointments_query-field-definitions.go 3.0 KB
- cli/internal/cli/appointments_query-item.go 3.1 KB
- cli/internal/cli/appointments_query-user-defined-field-definitions.go 3.1 KB
- cli/internal/cli/appointments_query.go 7.6 KB
- cli/internal/cli/appointments_update-entity.go 8.6 KB
- cli/internal/cli/appointments_url-parameter-query-count.go 3.7 KB
- cli/internal/cli/appointments_url-parameter-query.go 3.6 KB
- cli/internal/cli/appointments.go 1.3 KB
- cli/internal/cli/auth.go 5.9 KB
- cli/internal/cli/billing-codes_query-count.go 7.8 KB
- cli/internal/cli/billing-codes_query-entity-information.go 3.0 KB
- cli/internal/cli/billing-codes_query-field-definitions.go 3.0 KB
- cli/internal/cli/billing-codes_query-item.go 3.1 KB
- cli/internal/cli/billing-codes_query-user-defined-field-definitions.go 3.1 KB
- cli/internal/cli/billing-codes_query.go 7.6 KB
- cli/internal/cli/billing-codes_url-parameter-query-count.go 3.7 KB
- cli/internal/cli/billing-codes_url-parameter-query.go 3.6 KB
- cli/internal/cli/billing-codes.go 1.0 KB
- cli/internal/cli/channel_workflow.go 9.4 KB
- cli/internal/cli/companies_alerts_company-child-create-entity.go 11 KB
- cli/internal/cli/companies_alerts_company-child-delete-entity.go 6.7 KB
- cli/internal/cli/companies_alerts_company-child-patch-entity.go 11 KB
- cli/internal/cli/companies_alerts_company-child-query-entity-information.go 3.3 KB
- cli/internal/cli/companies_alerts_company-child-query-field-definitions.go 3.3 KB
- cli/internal/cli/companies_alerts_company-child-query-item.go 3.3 KB
- cli/internal/cli/companies_alerts_company-child-query-user-defined-field-definitions.go 3.3 KB
- cli/internal/cli/companies_alerts_company-child-query.go 3.1 KB
- cli/internal/cli/companies_alerts_company-child-update-entity.go 11 KB
- cli/internal/cli/companies_alerts.go 1.2 KB
- cli/internal/cli/companies_attachments_company-child-create-entity.go 15 KB
- cli/internal/cli/companies_attachments_company-child-delete-entity.go 6.8 KB
- cli/internal/cli/companies_attachments_company-child-query-item.go 3.4 KB
- cli/internal/cli/companies_attachments_company-child-query.go 3.2 KB
- cli/internal/cli/companies_attachments.go 854 B
- cli/internal/cli/companies_contacts_company-child-create-entity.go 19 KB
- cli/internal/cli/companies_contacts_company-child-delete-entity.go 6.8 KB
- cli/internal/cli/companies_contacts_company-child-patch-entity.go 19 KB
- cli/internal/cli/companies_contacts_company-child-query-entity-information.go 3.3 KB
- cli/internal/cli/companies_contacts_company-child-query-field-definitions.go 3.3 KB
- cli/internal/cli/companies_contacts_company-child-query-item.go 3.3 KB
- cli/internal/cli/companies_contacts_company-child-query-user-defined-field-definitions.go 3.4 KB
- cli/internal/cli/companies_contacts_company-child-query.go 3.1 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.
- 3d ago Changed · +1 lines 2ee833f68335
- 6d ago First seen · 893 lines · 96 tokens per session scan A 47435183615f
autotask is a skill published in the GitHub repository Servosity/msp-skills (36 stars, last pushed 4d ago), with no licence file. It adds 96 tokens to every session and 11,802 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
monday-com
Monday.com workspace management via official MCP server. This skill should be used when creating, updating, moving, archiving, or deleting items/boards/groups on Monday.com, managing columns, adding comments, or querying workspace data. Supports both hosted and local MCP deployment with interactive setup guidance.
skill
Skill "skill" from abdulhamid-n/ticktick-mcp, covering ticktick skill, when to use, available mcp tools, behavior guidelines and creating tasks.
ticktick
AI-powered task management and productivity assistant. This skill activates whenever the user mentions a task, to-do, reminder, or something they need to do. Trigger phrases include "remind me to", "I need to", "don't let me forget", "add a task", "create a task", "what's on my list", "what's due today", "mark that as…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.