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 modest-curator478/claude-skills --skill consulting-engagement-setupgit clone --depth 1 https://github.com/modest-curator478/claude-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/modest-curator478/claude-skills/consulting-engagement-setup)<a href="https://agentmods.dev/skills/modest-curator478/claude-skills/consulting-engagement-setup"><img src="https://agentmods.dev/badge/skills/modest-curator478/claude-skills/consulting-engagement-setup/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/modest-curator478/claude-skills/consulting-engagement-setup"><img src="https://agentmods.dev/badge/skills/modest-curator478/claude-skills/consulting-engagement-setup.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 | $0.00223 | $0.02966 |
| Opus 5.5 | $0.00089 | $0.01186 |
| Sonnet 5.5 | $0.00045 | $0.00593 |
| Haiku 4.5 | $0.00022 | $0.00297 |
Grade A, and why
consulting-engagement-setup 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 2mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- consulting-engagement-setup — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 390 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Consulting Engagement Setup: Scoping, Pricing, and Protecting the Work
This skill sets up an independent consulting engagement correctly from the start. Most first-time consultants either underprice the work, underscope the deliverables, or both. The result is an engagement that expands without additional compensation, produces resentment, and ends the client relationship faster than the work would have ended it naturally.
The goal of this skill is not to protect the consultant from the client. It is to create a clear shared understanding of what is being purchased so that both sides can evaluate whether the work was done correctly. Ambiguity in scope is not a negotiating advantage. It is a liability that collects interest until it is paid with a damaged relationship.
HOW TO SET UP THIS SKILL
Provide:
- What the client has asked for, in their words if possible
- How the conversation started (referral, inbound, prior relationship)
- Whether a rate has been discussed or if that conversation is still ahead
- Your current read on what the client actually needs versus what they asked for
- Any constraints: timeline, budget signals, internal politics at the client
- Whether this is your first consulting engagement or you have done this before
The Conversation Before the Proposal
The most important conversation in a consulting engagement happens before any proposal is written. Most first-time consultants skip it because they are eager to win the work. Skipping it is the reason most engagements go wrong.
The pre-proposal conversation has one goal: understand the problem the client is actually trying to solve, not the solution they have already decided they want.
A client who says "we need someone to clean up our HubSpot" may actually need attribution rebuilt because the CEO is asking why marketing cannot show pipeline contribution. Cleaning up HubSpot is one step in that solution, not the solution itself. A consultant who scopes to the stated request will finish the cleanup and leave the client unsatisfied because the underlying problem is unchanged.
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.
- 2mo ago First seen · 390 lines · 223 tokens per session scan A 200b95276bdd
consulting-engagement-setup is a skill published in the GitHub repository modest-curator478/claude-skills (5 stars, last pushed 18d ago), licensed MIT. It adds 223 tokens to every session and 2,966 once invoked, about $0.0009 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 2026-08-31.
Other skills, from other repositories
internal-comms
Use when announcing a reorg, tool rollout, policy change, leadership change, layoff or acquisition internally. Builds the announcement with changeannouncementbuilder.py and sequences it with commscalendarbuilder.py.
knowledge-ops
Use when writing, checking or cleaning up SOPs and runbooks. Generates them with sopgenerator.py, checks 5W2H completeness and links with runbookvalidator.py and ingests an existing knowledge base with kbingester.py.
procurement-optimizer
Use for a SaaS audit, category spend review or supplier consolidation. Categorizes spend with spendcategorizer.py, finds slow purchasing with purchasingcycleanalyzer.py and sizes consolidation with supplierconsolidation.py.
capacity-planner
Use when sizing an ops or support team, building a headcount plan or checking utilization risk. Models queues with Erlang C in capacitymodeler.py, analyzes utilization with utilizationanalyzer.py and orders hires with hiringsequencer.py.
chief-customer-officer-advisor
Use for retention strategy, customer segmentation or CS team sizing decisions (GRR vs NRR, churn causes, pooled vs named CSMs). Runs retentiondecompositionanalyzer.py, customersegmentationdesigner.py and cscoveragecalculator.py.
company-os
Use when choosing or setting up how the company runs: EOS, Scaling Up or OKRs, accountability chart, scorecard, meeting rhythm, quarterly rocks.