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 peterod99/consultant-skills --skill retainer-architecturegit clone --depth 1 https://github.com/peterod99/consultant-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/peterod99/consultant-skills/retainer-architecture)<a href="https://agentmods.dev/skills/peterod99/consultant-skills/retainer-architecture"><img src="https://agentmods.dev/badge/skills/peterod99/consultant-skills/retainer-architecture/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/peterod99/consultant-skills/retainer-architecture"><img src="https://agentmods.dev/badge/skills/peterod99/consultant-skills/retainer-architecture.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 | $0.00039 | $0.01074 |
| Opus 5 | $0.00019 | $0.00537 |
| Sonnet 5 | $0.00008 | $0.00215 |
| Haiku 4.5 | $0.00004 | $0.00107 |
Grade A, and why
retainer-architecture 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 12d 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Retainer Architecture
When to use
Your clients hire you for one-off projects (3–6 month engagements). You finish. They come back 6 months later with a new project. You want to turn this into recurring monthly revenue, so you're not starting from zero every 6 months. You need a framework for converting project-to-project chaos into stable, predictable income.
The framework
- Identify the recurring need: What problem does your client face every month that you solve every time they hire you? (e.g., sales funnel optimization, content calendar planning, team coaching). Not every project work converts; only work with a clear monthly heartbeat.
- Define retainer scope as ongoing access, not deliverables: A project gives 3 reports. A retainer gives 2–3 hours of your availability per month. Scope is "advising on sales strategy" not "deliver 2 emails + 1 audit." Availability beats deliverables.
- Price as 1.5–2x the equivalent project rate, monthly: A $10K project typically requires 4 months of your time at $2.5K/month. A retainer offering the same value costs $4K–5K/month because it's recurring, predictable, and requires lighter infrastructure. Never price retainer = project fee ÷ months. That's underselling.
- Anchor the retainer to an outcome, not a task list: "Grow your email list" or "Optimize your sales process" beats "Monthly strategy call + email feedback." Outcomes allow you to pivot tactics within the scope. Tasks lock you in.
- Lock in longer-term commitments: Retainers work at 3–12 months minimum, not month-to-month. Shorter terms destroy value: you spend Month 1 onboarding, Month 2–3 delivering, Month 4 they cancel. Require 6+ month minimums. This is non-negotiable for stability.
How to apply it
A fractional sales director works with 3-person SAAS startups. Each founder hires her for a 4-month "Sales Playbook" engagement: she audits pipeline, designs rep workflow, trains the team, hands off. The project is $8K. She finds that 60% rehire her 6 months later for "help us scale to 2 reps" or "our open rate dropped, audit our messaging." Patterns emerge.
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.
- 12d ago First seen · 36 lines · 39 tokens per session scan A 995e607ba33b
retainer-architecture is a skill published in the GitHub repository peterod99/consultant-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 39 tokens to every session and 1,074 once invoked, about $0.0002 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.
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.
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…
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…
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.
good-morning
Daily morning briefing that pulls calendar, tasks, pipeline, and outreach data into one view.
cold-email
Write cold outreach emails using signal-based, pain-first messaging. Improves itself over time.