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 panaversity/agentfactory-business-plugins --skill task-intelligencegit clone --depth 1 https://github.com/panaversity/agentfactory-business-pluginsWrote 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/panaversity/agentfactory-business-plugins/task-intelligence)<a href="https://agentmods.dev/skills/panaversity/agentfactory-business-plugins/task-intelligence"><img src="https://agentmods.dev/badge/skills/panaversity/agentfactory-business-plugins/task-intelligence/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/panaversity/agentfactory-business-plugins/task-intelligence"><img src="https://agentmods.dev/badge/skills/panaversity/agentfactory-business-plugins/task-intelligence.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 | $0.00083 | $0.00999 |
| Opus 5.5 | $0.00033 | $0.00400 |
| Sonnet 5.5 | $0.00017 | $0.00200 |
| Haiku 4.5 | $0.00008 | $0.00100 |
Grade A, and why
task-intelligence 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 1mo 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TASK INTELLIGENCE WORKFLOW
STEP 1 — LOAD CONTEXT
Read work.local.md in the current working directory.
If it does not exist, tell the user to run /agentic-office:setup first.
STEP 2 — IDENTIFY REQUEST TYPE
TYPE 1: CAPTURE (from brain dump / meeting notes / messages) Purpose: Rapidly capture and structure unorganised input. Input: Raw notes, brain dump, meeting output, messages — any format Output: Structured, prioritised list with owners and deadlines
TYPE 2: DAILY PRIORITISATION Purpose: Determine what to work on today from a larger set. Input: Full list (from work.local.md or provided) Output: Today's critical path (3-5 items) + schedule suggestion
TYPE 3: WEEKLY PLANNING Purpose: Set the week's priorities before it begins. Input: Project statuses; open delegations; upcoming deadlines Output: Week-ahead critical path; delegation candidates; decision items
TYPE 4: BACKLOG REVIEW Purpose: Audit the backlog — drop dead items; re-prioritise the rest. Input: Current backlog Output: Kept / dropped / re-prioritised list with rationale
TYPE 5: CROSS-DOMAIN PLAN Purpose: Generate an integrated action plan for a scenario that spans multiple functions (HR + Finance + Ops, etc.) Output: Items by function; dependencies; delegations; timeline
STEP 3 — EXECUTE WITH PRIORITY SORTING
OUTPUT STRUCTURE:
CAPTURE — [Date]
================================================================
[N] items captured | [N] overdue | [N] delegation candidates
-- P1 — URGENT / HIGH IMPACT ---------------------------------
[ ] [ITEM-NNN] [Title]
Context: [Why this matters; what it connects to]
Due: [Specific date or "today"]
Project: [Project name from work.local.md]
Action: [Specific first action — not vague]
Delegate: [If applicable — to whom]
Note: [Any sensitivity or communication guidance]
-- P2 — IMPORTANT / THIS WEEK --------------------------------
[Same structure]
-- P3 — STANDARD / BACKLOG -----------------------------------
[Same structure — briefer]
-- DELEGATION CANDIDATES --------------------------------------
[Item] → [Person from work.local.md] (with brief note on approach)
-- BLOCKED / AT RISK ------------------------------------------
[Any item that cannot proceed without something else; name the blocker]
================================================================
What ships with it
2 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.
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.
- 1mo ago First seen · 119 lines · 83 tokens per session scan A f10ad16caca4
task-intelligence is a skill published in the GitHub repository panaversity/agentfactory-business-plugins (36 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 83 tokens to every session and 999 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
memory-manage
Manage Active updates, atomic session handoffs, and human-gated Long-Term proposals. Use when asked to remember something, preserve a decision, log meaningful work, or review memory.
wrap-up
End-of-session confidence and blind-spot review. Use when closing meaningful work, before committing to action, or when the user asks what is missing or uncertain.
apple-platform-automation
Manage Apple/macOS personal apps and device workflows from Hermes, including Apple Notes, Reminders, Find My, iMessage/SMS, and UI automation. Use when a task involves Apple ecosystem data or macOS-only CLIs such as memo, remindctl, imsg, FindMy.app, AppleScript, or Peekaboo.
file_engine
Create, convert (including DOCX to PDF), patch, and replace Knowledge files through one file-engine workflow.
dashboard-module-builder
Use this skill when the user asks Manor AI to add, edit, remove, rearrange, or personalize content on their Dashboard, including requests such as "show daily news", "add a stock module", or "change this dashboard module". It generates a private, loadable Dashboard module and submits it for live preview instead of…
mcp_gmail
Operate the user's connected Gmail account through the Gmail MCP. Use when the user asks to read, search, summarize, send, reply to, draft, label, archive, or triage email on their Gmail / Google Mail account.