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 Stallin-Sanamandra/b2b-saas-marketing-skills --skill pipeline-attribution-narratorgit clone --depth 1 https://github.com/Stallin-Sanamandra/b2b-saas-marketing-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/stallin-sanamandra/b2b-saas-marketing-skills/pipeline-attribution-narrator)<a href="https://agentmods.dev/skills/stallin-sanamandra/b2b-saas-marketing-skills/pipeline-attribution-narrator"><img src="https://agentmods.dev/badge/skills/stallin-sanamandra/b2b-saas-marketing-skills/pipeline-attribution-narrator/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/stallin-sanamandra/b2b-saas-marketing-skills/pipeline-attribution-narrator"><img src="https://agentmods.dev/badge/skills/stallin-sanamandra/b2b-saas-marketing-skills/pipeline-attribution-narrator.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 | $0.00087 | $0.05080 |
| Opus 5 | $0.00044 | $0.02540 |
| Sonnet 5 | $0.00017 | $0.01016 |
| Haiku 4.5 | $0.00009 | $0.00508 |
Grade A, and why
pipeline-attribution-narrator 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 — 450 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pipeline Attribution Narrator
Transform raw campaign data into attribution models and decision-ready narratives. Built for demand gen leaders who own a pipeline number and need to explain what's working, what isn't, and where to reallocate.
Why This Skill Exists
Most marketing teams can pull campaign data. Few can answer the questions leadership actually asks:
- "Why did pipeline drop 18% this month?"
- "Should we increase the ABM budget or double down on paid search?"
- "What's the CAC payback period by segment?"
- "If we cut channel X, what happens to pipeline next quarter?"
The gap isn't data access. It's the translation layer between raw numbers and decisions. Attribution models produce tables. Leadership needs narratives. This skill builds both.
When to Use This Skill
- Building or selecting a pipeline attribution model
- Preparing a monthly pipeline report for CEO/VP/board
- Diagnosing why pipeline missed target in a given period
- Modeling budget reallocation scenarios (shift $X from channel A to channel B)
- Comparing channel efficiency across geos or segments
- Translating attribution data into stakeholder-ready narratives
- Evaluating whether your attribution approach needs to change
- Preparing for quarterly business reviews
When NOT to Use This Skill
- Lead scoring or MQL definitions (different problem, different skill)
- Campaign creative optimization (use a CRO or ad creative skill)
- Real-time bidding or media buying decisions (too operational for this skill)
- Attribution platform setup/configuration (this is strategic, not technical)
- Single-channel performance analysis (this skill is cross-channel by design)
Attribution Model Selection
The Models
No model is "correct." Each answers a different question. Pick based on what decision you need to make, not what feels most sophisticated.
| Model | How It Works | Best For | Worst For |
|---|---|---|---|
| First Touch | 100% credit to the first interaction | Answering "what fills the top of funnel?" | Understanding what closes deals |
| Last Touch | 100% credit to the final interaction before conversion | Answering "what triggers the conversion?" | Understanding what builds awareness |
| Linear | Equal credit to every touchpoint | Getting a balanced view when you have no hypothesis | Making reallocation decisions (everything looks equal) |
| Time Decay | More credit to touches closer to conversion | Understanding acceleration and late-stage influence | Evaluating brand and awareness investments |
| W-Shaped | 40% first touch, 20% middle touches, 40% opportunity creation touch | B2B SaaS with defined MQL-to-SQL handoff | Short sales cycles or single-touch conversions |
| Full Path | 22.5% first touch, 22.5% lead creation, 22.5% opportunity creation, 22.5% close, 10% middle | Enterprise B2B with long multi-touch cycles | Companies without clean stage data in CRM |
| Custom/Weighted | You define weights per stage based on your data | Mature teams with enough data to validate weights | Teams just starting attribution (overengineered) |
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 · 450 lines · 87 tokens per session scan A 69f1eff0b8d7
pipeline-attribution-narrator is a skill published in the GitHub repository Stallin-Sanamandra/b2b-saas-marketing-skills (5 stars, last pushed 4mo ago), licensed MIT. It adds 87 tokens to every session and 5,080 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 2026-08-31.
Other skills, from other repositories
fedramp
Expert guidance for FedRAMP certification and compliance under CR26 (FedRAMP Consolidated Rules for 2026). Use this skill whenever a user asks about FedRAMP authorization, ATO (Authority to Operate), cloud security for federal government, NIST SP 800-53 controls, CSP compliance, or any of the core FedRAMP document…
iso42001
Expert ISO 42001 AI Management System (AIMS) compliance advisor. Use this skill whenever a user asks about ISO/IEC 42001:2023, AI governance, AI management systems, AI risk assessment, AI system impact assessment, Annex A controls for AI, Statement of Applicability for AI systems, AI policy, responsible AI, AI…
eu-cra
Expert EU Cyber Resilience Act (CRA) advisor for Regulation (EU) 2024/2847 — mandatory cybersecurity and vulnerability handling requirements for all products with digital elements (PDEs) sold in the EU. Use this skill for gap analysis, product classification (Default / Class I / Class II), conformity assessment route…
nist-800-53
NIST SP 800-53 Rev 5 compliance advisor — all 20 control families (AC, AT, AU, CA, CM, CP, IA, IR, MA, MP, PE, PL, PM, PS, PT, RA, SA, SC, SI, SR), Low/Moderate/High baseline selection, FIPS 199/200 system categorization, control tailoring and overlays, privacy controls (PT family), supply chain risk management (SR…
hipaa-compliance
Expert HIPAA compliance assistant for healthcare and software contexts. Use this skill whenever the user mentions HIPAA, PHI (Protected Health Information), ePHI, covered entities, business associates, healthcare data privacy, medical records, health information security, BAA (Business Associate Agreements), or any…
GRC & Compliance
Governance, risk, and compliance — risk assessment and scoring, control mapping across NIST CSF 2.0 / ISO 27001:2022 / SOC 2 / CIS Controls v8, gap analysis, audit evidence preparation, and security policy generation.