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 delegationgit 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/delegation)<a href="https://agentmods.dev/skills/panaversity/agentfactory-business-plugins/delegation"><img src="https://agentmods.dev/badge/skills/panaversity/agentfactory-business-plugins/delegation/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/delegation"><img src="https://agentmods.dev/badge/skills/panaversity/agentfactory-business-plugins/delegation.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 | $0.00078 | $0.00984 |
| Opus 5 | $0.00039 | $0.00492 |
| Sonnet 5 | $0.00016 | $0.00197 |
| Haiku 4.5 | $0.00008 | $0.00098 |
Grade A, and why
delegation 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DELEGATION 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.
Load the delegatee's person entry from work.local.md Layer 2 (Team).
STEP 2 — PRODUCE DELEGATION RECORD
OUTPUT STRUCTURE:
DELEGATION RECORD — [Description]
================================================================
Delegated to: [Person name — from work.local.md if available]
Delegated by: [Your name from work.local.md personal layer]
Date: [Today]
Due: [Specific date and time — not ASAP]
DELIVERABLE:
What: [Precise description of what must be produced]
Format: [Slides / doc / data / email / verbal — specific]
Length: [If relevant — 2-page; 10 slides; 500 words]
CONTEXT:
Purpose: [Why this is needed; what decision it supports]
Audience: [Who will see/use this output]
Key question the output should answer: [The most important question]
CONSTRAINTS:
What not to do: [Any specific exclusions or out-of-scope items]
Prior work: [Any existing documents or decisions to build from]
HANDOFF COMMUNICATION (ready to send):
[Draft message in the delegatee's preferred channel and style,
loaded from work.local.md person entry]
FOLLOW-UP PLAN:
Confirmation due: [Time — typically EOD today for same-week items]
Check-in: [If no confirmation: follow up at this time]
Escalation: [If no delivery by [date - N days]: flag in digest]
================================================================
STEP 3 — LOG THE DELEGATION
Add an entry to the delegation log in work.local.md:
- task: "[Description]"
delegated_to: "[Person]"
delegated_by: "[You]"
date_delegated: "[Date]"
due_date: "[Date]"
confirmed: false
status: "PENDING CONFIRMATION"
deliverable: "[What was requested]"
Handoff Communication Calibration
Apply the delegatee's communication style from work.local.md:
PERSON prefers async / written: Draft a Slack message or email; not a meeting request
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.
- 9d ago First seen · 130 lines · 78 tokens per session scan A ee75a23167b9
delegation is a skill published in the GitHub repository panaversity/agentfactory-business-plugins (29 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 78 tokens to every session and 984 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 2026-08-30.
Other skills, from other repositories
kanban-codex-lane
Use when a Hermes Kanban worker wants to run Codex CLI as an isolated implementation lane while Hermes keeps ownership of task lifecycle, reconciliation, testing, and handoff.
prd-review-framework
Use when reviewing a PRD for goal clarity, scope, assumptions, and implementation readiness.
kanban
Hermes Kanban multi-agent workflow — orchestrator decomposition playbook and worker pitfalls/examples for routing work across profiles through the durable SQLite board.
codebase-audit-and-roadmap
Audit a codebase from a user reference and produce a structured feature inventory, gap analysis, and build-plan PRD.
content-production-workflow
End-to-end workflow for creative review gates, content drafting, and publishing to blogs, Notion, and social channels with explicit approval checkpoints.
client-success-and-retention
Use when designing client delivery for a coaching/agency program, hiring or running a Client Success Manager / success coach, handling a struggling or refund-requesting client, setting onboarding-call and check-in cadence, improving retention and continuity, or building/optimising a booking confirmation page (the…