delivery-model-selection

delivery-model-selection is a skill for Claude Code, Codex from peterod99/consultant-skills. It costs 29 tokens per session (1,216 once invoked), scanned A, original, MIT.

A framework for choosing how a consulting service is delivered: fully done for the client, jointly with the client, self-directed, in person, online, or asynchronously.

In plain words
What is it for?
Use it when designing a consulting offer and deciding who performs the work, how much support to provide, and whether delivery happens in person or remotely. It also considers how those choices affect pricing and client capacity.
Why use it?
It helps match the amount of client involvement and delivery time to the client's experience, available time, and willingness to do the work.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when designing a consulting offer and deciding who performs the work, how much support to provide, and whether delivery happens in person or remotely. It also considers how those choices affect pricing and client capacity.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/peterod99/consultant-skills/delivery-model-selection
Install

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.

Any agent
npx skills add peterod99/consultant-skills --skill delivery-model-selection
Clone the repo
git clone --depth 1 https://github.com/peterod99/consultant-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for delivery-model-selection

README.md
[![agentmods](https://agentmods.dev/badge/skills/peterod99/consultant-skills/delivery-model-selection/github.svg)](https://agentmods.dev/skills/peterod99/consultant-skills/delivery-model-selection)
Your own site
<a href="https://agentmods.dev/skills/peterod99/consultant-skills/delivery-model-selection"><img src="https://agentmods.dev/badge/skills/peterod99/consultant-skills/delivery-model-selection/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.

agentmods 80×15 button for delivery-model-selection

Your own site · 80×15
<a href="https://agentmods.dev/skills/peterod99/consultant-skills/delivery-model-selection"><img src="https://agentmods.dev/badge/skills/peterod99/consultant-skills/delivery-model-selection.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,216 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00029 $0.01216
Opus 5 $0.00015 $0.00608
Sonnet 5 $0.00006 $0.00243
Haiku 4.5 $0.00003 $0.00122

Measured 9d ago against content hash 80ccb1a90fc8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

delivery-model-selection 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.

delivery-model-selection/SKILL.md · 38 lines

How it starts

The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Delivery Model Selection

When to use

You're designing a new offer and need to decide how hands-on you'll be. Is this done-for-you (you deliver everything), done-with-you (you guide the client through the work), or DIY (they do the work with your framework)? And will you deliver in-person, virtual, or asynchronously? Your answer depends on client maturity, your time constraints, and your price ceiling.

The framework

  1. Assess client maturity and willingness: Done-for-you works when the client is resource-constrained, has no in-house expertise, or is buying the solution, not the education. Done-with-you works when the client wants to learn and has 5+ hours/month to participate. DIY works only for clients who have solved 60% of the problem and need the last 40%.
  2. Map your time commitment per delivery model: Done-for-you: high touch, 80% client conversations + execution. Done-with-you: medium touch, 50% teaching + 50% execution. DIY: low touch, 20% support + 80% self-service content. The model determines your price ceiling and how many clients you can carry at once.
  3. Choose the time/location axis independently: In-person (you travel) adds scarcity premium (20–30% price bump) but limits volume (you're booked out in weeks). Virtual (video calls) is the default; async (Slack + recordings) is cheapest to deliver but requires client self-direction. Match to offer tier: $50K offer = in-person, $10K = virtual, $2K = async.
  4. Validate against your positioning: If you position as a high-touch, premium advisor, done-for-you in-person earns the price. If you're positioned as an educator / framework provider, DIY or done-with-you virtual wins. Delivery model must reinforce your positioning. (A $50K offer with pure async delivery signals you don't care; clients reject it.)
  5. Run a soft test with early clients: Offer the same service in two delivery models and track NPS, completion rate, referrals, and revenue. Done-for-you might earn 30% more but require 50% more time. The math determines scale.

Read the full file on GitHub · 38 lines

Changes

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.

  1. 9d ago First seen · 38 lines · 29 tokens per session scan A 80ccb1a90fc8

Subscribe to this mod's changes

delivery-model-selection is a skill published in the GitHub repository peterod99/consultant-skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 29 tokens to every session and 1,216 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

strategy-consulting-visualization

Use when turning any content into clear, professional visualizations - board slides, reports, proposals, research summaries, training materials, technical diagrams, infographics, process flows, timelines, benchmarks, waterfall charts, or data-backed visual specs for any audience.

kgraph57/mckinsey-style-visualization-skill · 58 tokens

mckinsey-market-research-deck

End-to-end playbook for producing a top-tier, McKinsey-style market-research deck (HTML page-turning presentation + print-ready PDF) for a brand or product category. Covers the research methodology (TAM/SAM/SOM bottom-up, Good/Better/Best framework, competitor profiling, customer pain points, unit economics, business…

norahe0304-art/30x-mckinsey-research-deck · 188 tokens

mckinsey-deck

Turn any content into a top-tier McKinsey-style deck — a 1280×720 page-turning HTML presentation that also prints to a clean per-slide PDF. Use when the user wants a "McKinsey-style deck / presentation", a polished slide deck or PDF from notes/content, an executive/board/investor deck, or to "make slides / a deck / a…

norahe0304-art/30x-mckinsey-research-deck · 119 tokens

setup

Interactive setup wizard that configures the GTM Engine for a new user. Collects company context, team info, ICP, personas, messaging, and signals, then generates all config and context files.

himanshusaleria/gtm-engine · 0 tokens

good-morning

Daily morning briefing that pulls calendar, tasks, pipeline, and outreach data into one view.

himanshusaleria/gtm-engine · 0 tokens

cold-email

Write cold outreach emails using signal-based, pain-first messaging. Improves itself over time.

himanshusaleria/gtm-engine · 21 tokens