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 event4u-app/agent-config --skill churn-preventiongit clone --depth 1 https://github.com/event4u-app/agent-configWrote 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/event4u-app/agent-config/churn-prevention)<a href="https://agentmods.dev/skills/event4u-app/agent-config/churn-prevention"><img src="https://agentmods.dev/badge/skills/event4u-app/agent-config/churn-prevention/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/event4u-app/agent-config/churn-prevention"><img src="https://agentmods.dev/badge/skills/event4u-app/agent-config/churn-prevention.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 | $0.00043 | $0.01874 |
| Opus 5 | $0.00022 | $0.00937 |
| Sonnet 5 | $0.00009 | $0.00375 |
| Haiku 4.5 | $0.00004 | $0.00187 |
Grade A, and why
churn-prevention 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 10d 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
churn-prevention
When to use
- Net retention dropped and the team cannot name which of the four churn causes is dominant — defence-spending is uniform when it should be cause-specific.
- A health score exists but does not predict — it tracks usage but misses relationship and fit signals — and CS plays are running on bad triggers.
- A board ask names "are we losing customers we should have kept, or customers who never fit?" — the answer requires the four-way classification, not a single number.
Do NOT use to fix days 0–30 onboarding (route to
onboarding-design), drive upsell or expansion (route to
expansion-playbook), or build product-led retention loops (route
to retention-loops).
Cognition cluster
- Mental model 30 — Inversion. Do not ask "how do we keep this
account?" — ask "name the reason this account will leave." The
inversion forces a cause; the cause picks the move. See
docs/contracts/mental-models.md§ 30. - Mental model 16 — Leading vs. lagging indicators. Cancellation
is lagging; usage-decay, relationship-decay, and fit-mismatch
signals are leading. A health score built on lagging signals can
only confirm churn after the cancel request lands. See
mental-models.md§ 16. - Mental model 3 — Pareto (80/20). ~20 % of accounts carry ~80 %
of revenue risk. Uniform health-monitoring across the book is
theatre; weighted monitoring is reasoning. See
mental-models.md§ 3. - Context-spine — product + customer-segment. Read the
product slot for which capabilities the segment was sold
(value-churn lives here when capability and pitch diverged), and
the customer-segment slot for the segment's switch-event
patterns — fit-churn shows up early in segments whose switch
event differs from the ICP. See
context-spine.
Procedure
Step 0: Inspect — classify the last 20 churn events
Inspect the most recent 20 cancellation events. Tag each as one of:
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.
- 10d ago First seen · 165 lines · 43 tokens per session scan A 091612ab5f27
churn-prevention is a skill published in the GitHub repository event4u-app/agent-config (10 stars, last pushed today), licensed MIT. It adds 43 tokens to every session and 1,874 once invoked, about $0.0002 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
save-progress
Save current project task progress to local task state file for cross-session continuity. Use when the user asks to save progress, uses an equivalent localized trigger phrase, the session is interrupted, or the user wants to resume work later. Writes to .claude/project-task-state.json so next session can load it via…
meta-theory
MetaKim executable governance dispatcher. It classifies the run, loads only needed references, preserves foundational capabilities and runtime-native abilities, routes owner + weapon + dependency + runtime + OS + verification, and closes only with evidence, intent acceptance, and writeback decision.
same-set-reusable-flow-for-project-file-inventor
Reusable MetaKim file inventory classification flow. It helps separate durable sources, generated evidence, runtime mirrors, temporary state, and risky unknowns before cleanup or commit.
starreel-drama-production
Operating skill for any AI agent driving the StarReel short-drama production pipeline (script → rewrite → extract → portraits + sheets → storyboards → frames → video → voiceover → final cut) over MCP or REST. Covers the ordered workflow, the entry-point decision table (which channel each kind of customer material…
seedance-20
Generate and direct cinematic AI videos with Seedance 2.0 (ByteDance/Dreamina/Jimeng). Covers text-to-video, image-to-video, video-to-video, and reference-to-video workflows with @Tag asset references, multi-character scenes, audio design, and post-processing. Use when making AI video, writing Seedance prompts…
monorepo-management
Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.