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 clamp-sh/analytics-skills --skill channel-and-funnel-qualitygit clone --depth 1 https://github.com/clamp-sh/analytics-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/clamp-sh/analytics-skills/channel-and-funnel-quality)<a href="https://agentmods.dev/skills/clamp-sh/analytics-skills/channel-and-funnel-quality"><img src="https://agentmods.dev/badge/skills/clamp-sh/analytics-skills/channel-and-funnel-quality/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/clamp-sh/analytics-skills/channel-and-funnel-quality"><img src="https://agentmods.dev/badge/skills/clamp-sh/analytics-skills/channel-and-funnel-quality.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 | $0.00077 | $0.03837 |
| Opus 5 | $0.00039 | $0.01919 |
| Sonnet 5 | $0.00015 | $0.00767 |
| Haiku 4.5 | $0.00008 | $0.00384 |
Grade A, and why
channel-and-funnel-quality 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 — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Channel and funnel quality
The specialist skill for judging quality, not just volume. Most "which channel is best" answers get the wrong channel because they look at sessions or even conversion rate in isolation. The right answer is a matrix.
Read analytics-diagnostic-method first if you haven't. This skill assumes you know MECE, triangulation, sample size, and Simpson's paradox. It adds channel-specific and funnel-specific mechanics.
Opening moves
- Read
analytics-profile.md. The model (B2B SaaS vs ecom vs lead gen) dictates which benchmark table applies and what "quality" even means. - Nail down the primary conversion event. Volume of "users who clicked the CTA" and volume of "paid signups" are not the same question.
- Decide the time window. Recent-7-days is too short for most B2B funnels (sales cycle is longer than the window). Use 30 or 90 days for B2B; 7-14 days is fine for high-velocity consumer funnels.
The quality matrix
A channel or segment is never "good" or "bad" alone. It has three dimensions and you need all three:
Volume Engagement Conversion
(sessions) (pages/session, (CVR to primary
duration, depth) event, revenue/visitor)
Direct high high high → flagship; defend
Organic high high medium-high → compound invest
Referral medium high medium-high → cultivate
Paid search medium medium medium → maintain, scale only if CAC allows
Email medium high very high → feed the list
Paid social high low low → vanity unless targeted well
Affiliates varies low-medium low-medium → audit for fraud, gate payouts
Unknown bots high very low zero → exclude, not a channel
Use this as a default sorting key, not a verdict. A specific channel in a specific business can land anywhere in the matrix. The point is: a channel with high volume and low engagement is vanity traffic; a channel with low volume and high conversion is probably underinvested.
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 · 281 lines · 77 tokens per session scan A c7dc0f03564f
channel-and-funnel-quality is a skill published in the GitHub repository clamp-sh/analytics-skills (8 stars, last pushed 3mo ago), licensed MIT. It adds 77 tokens to every session and 3,837 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
treat
Prune bloated session with a prescription. Removes progress ticks, stale reads, duplicate content, and more.
guard
Protect Claude Code sessions from context overflow by running a background daemon that monitors session size and auto-prunes before compaction hits. Use when the user says "guard", "protect session", "context getting long", "prevent compaction", "session management", or is running agent teams that need continuous…
cozempic-doctor
Run health checks on Claude Code configuration and sessions. Use when troubleshooting Claude Code issues. (cozempic — does not shadow Claude Code's built-in /doctor).
diagnose
Analyze Claude Code session bloat — shows token count, context usage %, and bloat breakdown. Use when the user asks about session size, context usage, or when you notice the context window is getting full.
reload
Treat the current session and auto-resume in a new terminal window.
radin-execute
Work through a project's whole backlog: prioritize every task, execute each via a sub-agent, commit after each. Use when the user wants the entire backlog processed ("work through my backlog"), not one named task. Delegates all implementation to sub-agents; clarifies ambiguity by asking the user rather than guessing.