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 indranilbanerjee/neels-plugins --skill client-proposalgit clone --depth 1 https://github.com/indranilbanerjee/neels-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/indranilbanerjee/neels-plugins/client-proposal)<a href="https://agentmods.dev/skills/indranilbanerjee/neels-plugins/client-proposal"><img src="https://agentmods.dev/badge/skills/indranilbanerjee/neels-plugins/client-proposal/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/indranilbanerjee/neels-plugins/client-proposal"><img src="https://agentmods.dev/badge/skills/indranilbanerjee/neels-plugins/client-proposal.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 | $0.00031 | $0.01236 |
| Opus 5.5 | $0.00012 | $0.00494 |
| Sonnet 5.5 | $0.00006 | $0.00247 |
| Haiku 4.5 | $0.00003 | $0.00124 |
Grade A, and why
client-proposal 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 2d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/digital-marketing-pro:client-proposal
Purpose
Generate a professional marketing agency proposal or pitch document for a prospective client. Covers strategic analysis, service scope, deliverables, pricing, and team positioning to win new business or formalize an existing engagement with a polished, ready-to-customize document.
Input Required
The user must provide (or will be prompted for):
- Client business name and industry: Who the proposal is for and their vertical/market segment
- Services requested: Which marketing services are in scope (SEO, PPC, social, content, email, strategy, creative, analytics, etc.)
- Estimated budget range: Client's stated or expected budget for marketing services (monthly or annual)
- Timeline: Engagement duration — 3-month pilot, 6-month contract, 12-month retainer, or project-based with defined milestones
- Key challenges/goals: What the client is trying to achieve, problems they need solved, or opportunities they want to capture
- Competitive context: Key competitors, market pressures, or differentiation challenges the client faces
- Decision criteria: What matters most to the client — price, expertise, speed, industry experience, team size, or technology
- Proposal format: Full written proposal, pitch deck outline, or scope-of-work document
- Existing relationship: New prospect, referral, existing client expansion, or RFP response
- Internal team available: Agency team members who would staff the account (for team bio section)
Process
- Load brand context: Read
~/.claude-marketing/brands/_active-brand.jsonfor the active slug, then load~/.claude-marketing/brands/{slug}/profile.json. Apply brand voice, compliance rules for target markets (skills/context-engine/compliance-rules.md), and industry context. The loaded brand should be the agency brand — the proposal will be written from the agency's perspective. Also check for guidelines at~/.claude-marketing/brands/{slug}/guidelines/_manifest.json— if present, load restrictions and relevant category files. Check for custom templates at~/.claude-marketing/brands/{slug}/templates/. Check for agency SOPs at~/.claude-marketing/sops/. If no brand exists, ask: "Set up a brand first (/digital-marketing-pro:brand-setup)?" — or proceed with defaults. - Research client industry benchmarks: Pull relevant industry performance data, typical marketing spend ratios, competitive landscape patterns, and common pain points for the client's vertical
- Define proposed scope of services: Map requested services to specific deliverables, ownership (agency vs. client), frequency, and dependencies between service lines
- Build deliverables matrix with timelines: Create a detailed breakdown of every deliverable, its cadence (weekly, monthly, quarterly), responsible party, and approval workflow
- Create KPI framework with realistic targets: Set measurable goals for each service line — baseline assumptions, 90-day targets, 6-month targets, and stretch goals tied to business outcomes
- Design pricing structure: Develop 2-3 pricing options — retainer-based, project-based, or performance-based models with clear scope boundaries, overage terms, and upgrade paths
- Include case study references: Frame placeholders for relevant case studies or past results that demonstrate capability in the client's industry, service area, or challenge type
- Draft executive summary: Write a compelling 1-page overview that connects the client's specific challenges to the proposed solution and expected outcomes
- Build team and process overview: Outline the account team structure, communication cadence (weekly calls, monthly reports, quarterly reviews), reporting rhythm, and escalation process
- Include terms and conditions framework: Draft standard engagement terms covering scope change process, payment terms, IP ownership, confidentiality, data handling, performance guarantees, and termination clauses
- Add competitive differentiation: Articulate why the agency is the right choice based on the client's stated decision criteria — without naming competitors directly
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.
- 2d ago First seen · 62 lines · 31 tokens per session scan A 6d2759d9326e
client-proposal is a skill published in the GitHub repository indranilbanerjee/neels-plugins (6 stars, last pushed 2d ago), licensed MIT. It adds 31 tokens to every session and 1,236 once invoked, about $0.0001 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 2026-10-12.
Other skills, from other repositories
continuous-improvement-loop
Run the Part 12 continuous improvement loop into a quarterly brief for leadership. "produce the quarterly improvement brief".
competitor-pages
Build competitor comparison pages: X-vs-Y, alternatives and roundups, with schema. "create a vs page".
yearly-planner
Produce the Part 8 yearly planner: quarterly themes and monthly initiatives. "plan the whole year month by month".
attribution-report
Run attribution on real conversion paths, comparing models. "which channels actually drive revenue".
validate-output
Validate content structure against a schema: sections, word counts. "scan for leftover placeholders".
add-integration
Add a custom MCP integration: scaffold the server, write .mcp.json, test it. "add a new MCP server".