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 win-loss-analysisgit 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/win-loss-analysis)<a href="https://agentmods.dev/skills/modest-curator478/claude-skills/win-loss-analysis"><img src="https://agentmods.dev/badge/skills/modest-curator478/claude-skills/win-loss-analysis/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/win-loss-analysis"><img src="https://agentmods.dev/badge/skills/modest-curator478/claude-skills/win-loss-analysis.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 | $0.00209 | $0.01914 |
| Opus 5 | $0.00105 | $0.00957 |
| Sonnet 5 | $0.00042 | $0.00383 |
| Haiku 4.5 | $0.00021 | $0.00191 |
Grade A, and why
win-loss-analysis 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 11d 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.
This is a copy
100% identical to win-loss-analysis — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Win/Loss Analysis: The Diagnostic That Improves Everything Downstream
This skill structures a win/loss analysis program that actually changes how the team goes to market. Most companies do some version of win/loss analysis. Almost none do it in a way that produces findings specific enough to act on.
The failure mode is familiar: CRM closed/lost reason fields that contain nothing useful ("not the right time," "went with competitor," "budget"), post-loss debrief conversations with the sales rep that produce the rep's perspective rather than the prospect's, and quarterly summaries that confirm what leadership already believed rather than revealing something that changes a decision.
This skill encodes the practices that produce findings specific enough to change ICP definition, adjust messaging, inform pricing, and redirect channel investment. The analysis is only useful if it feeds back into something that changes.
HOW TO SET UP THIS SKILL
Provide:
- What data you currently have on lost deals: CRM closed/lost reasons, rep debrief notes, anything else
- Whether you have access to lost prospects for direct interviews
- The time period you want to analyze
- The primary question you are trying to answer: is this about a specific competitor, a specific market segment, a pricing problem, or general pattern identification?
- What decisions you want to be able to make differently as a result
Why CRM Closed/Lost Data Is Almost Always Wrong
Before building any analysis on CRM closed/lost data, understand its limitations. CRM reasons are entered by sales reps under time pressure, often days or weeks after the deal closed, based on whatever the rep believes happened rather than what the prospect said. Four structural problems make this data unreliable:
Reps rationalize losses. A deal lost because the rep did not follow up fast enough, or because the demo was poorly matched to the use case, will be logged as "not the right time" or "lost to competitor." The rep is not lying. They genuinely believe their interpretation. But the root cause is invisible in the data.
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.
- 11d ago First seen · 226 lines · 209 tokens per session scan A 23adfe5f4c08
win-loss-analysis is a skill published in the GitHub repository modest-curator478/claude-skills (4 stars, last pushed today), licensed MIT. It adds 209 tokens to every session and 1,914 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to win-loss-analysis, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
TEMPLATE
../../../agents/personas/TEMPLATE.md.
debug
Systematic debugging using error-detective and debugger agents instead of manual investigation. Triggers automatically on: error, bug, broken, failing, exception, stack trace, test failure. Orchestrates RCA-first approach with parallel agent investigation.
deep-context
Build deep codebase understanding using Capsule context, progressive-reader, and specialist agents instead of overwhelming main context. Triggers on: don't have context, understand codebase, learn about, need background. Implements progressive context building.
task-router
Decision matrix for choosing optimal approach to any task. Helps Claude decide when to delegate to sub-agents vs. working directly. Use when starting a new task or unsure of best approach.
workflow
Systematic task orchestration for complex multi-step tasks. Triggers automatically when detecting: complex task, multi-step work, coordinate, orchestrate, break down. Guides through Understand → Strategy → Plan → Execute → Verify phases for comprehensive systematic approach.
nextdns-cli
NextDNS CLI client best practices for installation, configuration, and management of DNS-over-HTTPS proxy. This skill should be used when installing NextDNS on routers, servers, or client devices, configuring DNS settings, managing the daemon, or troubleshooting DNS issues. Triggers on tasks involving NextDNS CLI…