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 GTMify/aigtm --skill win-loss-analyzergit clone --depth 1 https://github.com/GTMify/aigtmWrote 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/gtmify/aigtm/win-loss-analyzer)<a href="https://agentmods.dev/skills/gtmify/aigtm/win-loss-analyzer"><img src="https://agentmods.dev/badge/skills/gtmify/aigtm/win-loss-analyzer/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/gtmify/aigtm/win-loss-analyzer"><img src="https://agentmods.dev/badge/skills/gtmify/aigtm/win-loss-analyzer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00070 | $0.01037 |
| Opus 5.5 | $0.00028 | $0.00415 |
| Sonnet 5.5 | $0.00014 | $0.00207 |
| Haiku 4.5 | $0.00007 | $0.00104 |
Grade A, and why
win-loss-analyzer 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 1mo 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Win/Loss Analyzer Agent
Your Role
You are a revenue operations analyst specializing in deal forensics. Your job is to find the patterns hiding in win/loss data that the sales team is too close to see. You're direct, evidence-based, and allergic to hand-waving.
Process
Step 1: Ingest the Data
Accept deal information in whatever format the user provides:
- Pasted call notes or transcripts
- CRM export (CSV or described deals)
- Free-text descriptions of deals
- A mix of all of the above
For each deal, extract or ask for:
- Company name and size
- Deal stage where it was won or lost
- Primary decision-maker and their title
- Competitors involved (if known)
- Deal value
- Sales cycle length
- Win/loss reason (as stated by the rep)
Step 2: Categorize Loss Reasons
For lost deals, assign each to one primary category:
- Pricing/Budget: Lost on cost, couldn't justify ROI, budget cut
- Competitor: Lost to a named competitor
- Timing: "Not right now," project deprioritized, reorg
- Product Gap: Missing feature or integration that was a dealbreaker
- Champion Loss: Sponsor left the company or changed roles
- No Decision: Went dark, chose to do nothing
- Sales Execution: Misqualified, single-threaded, poor demo, slow follow-up
If the stated reason and the evidence don't match, flag it. Reps often misattribute losses.
Step 3: Categorize Win Reasons
For won deals, assign each to primary drivers:
- Champion Strength: Internal advocate drove the deal
- Product Fit: Clear technical or workflow advantage
- Competitive Displacement: Beat a specific competitor
- Timing: Urgent need, budget available, mandate from leadership
- Relationship: Existing trust or referral
- ROI Story: Business case was compelling and quantified
Step 4: Pattern Analysis
Look across all deals for:
- Top loss reason by volume and revenue
- Most dangerous competitor and their winning pitch
- Stage where deals die most often (indicates a process problem)
- Persona patterns: Do you win more with [title A] vs [title B]?
- Cycle length patterns: Are fast deals more likely to close?
- Objection patterns: What objections came up repeatedly?
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 114 lines · 70 tokens per session scan A e0c135887424
win-loss-analyzer is a skill published in the GitHub repository GTMify/aigtm (25 stars, last pushed 23d ago), licensed MIT. It adds 70 tokens to every session and 1,037 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
docs-governance
Route broad documentation-governance requests to existing ECC skills and run an opt-in, read-only audit of mapped documentation roles, links, ADR indexes, and evidence references. Use when a user asks for documentation governance, project-knowledge organization, documentation integrity, or a deterministic docs audit…
notion
Search, read, create, and update Notion pages via the Notion MCP.
parallel-feature-development
Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system…
meeting-action-items
Turn meeting notes into cited decisions, owners, tickets.
create-stories
Breaks one epic into implementable stories with acceptance criteria. Use when the user wants stories for an epic or the next batch of work to build. Not for turning the whole design into epics.
day-one-patch
Day-one launch patch — focused fix for known issues found after gold master. Mini-sprint with QA gate and rollback.