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 agentmods add skills/everywan-dev/claude-code-engineering/make-the-next-failure-loudnpx skills add everywan-dev/claude-code-engineering --skill make-the-next-failure-loudgit clone --depth 1 https://github.com/everywan-dev/claude-code-engineeringWrote 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/everywan-dev/claude-code-engineering/make-the-next-failure-loud)<a href="https://agentmods.dev/skills/everywan-dev/claude-code-engineering/make-the-next-failure-loud"><img src="https://agentmods.dev/badge/skills/everywan-dev/claude-code-engineering/make-the-next-failure-loud.svg" alt="Measured on agentmods" 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 | $0.00047 | $0.01163 |
| Opus 5 | $0.00023 | $0.00581 |
| Sonnet 5 | $0.00009 | $0.00233 |
| Haiku 4.5 | $0.00005 | $0.00116 |
Grade A, and why
make-the-next-failure-loud 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 4d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Make the next failure loud
Debugging a silent failure is a skill. Not needing it is better.
Every outage that took days to notice had the same root: nothing was watching the thing that broke, and something else was cheerfully reporting success. Adding observability afterwards feels like paperwork, which is why it is skipped, which is why the next one is silent too.
🔴 The question is never "what should we log?" It is "what would have told us, and how long would it have taken?" Answer that about the failure you just had, and you will know exactly what to add.
When to use this
- You have just finished an incident and are about to close it
- You are shipping something whose failure would produce no error
- Something is "monitored" but you cannot say what would page you
- A dashboard is green and you do not trust it
- Anything scheduled: jobs, syncs, backups, reports, certificate renewals
The procedure
1. Write the failure you just had as a sentence. "The export did not run for four days and nobody noticed." Keep it; every step below is measured against it.
2. Ask what signal would have contradicted the green. Not what would have shown the error — there was no error. What would have shown the absence:
| Instead of watching | Watch |
|---|---|
| "The process is running" | It finished, and when it last finished |
| "The endpoint returns 200" | The response contains what only a live system produces |
| "No errors in the log" | The log is still being written to at all |
| "The queue is healthy" | The queue is moving, and its oldest item's age |
| "Backups are configured" | A backup exists, is recent, and restores |
| "The certificate is valid" | Days remaining, alerting well before zero |
The pattern: watch for the expected thing happening, not for the unexpected thing failing. Absence is the failure mode that survives every other check.
3. Alert on the symptom a person would notice, at the threshold they would notice it. If a customer would care after one missed run, alert after one. An alert nobody acts on is worse than no alert, because it teaches people that alerts are noise.
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.
- 4d ago First seen · 102 lines · 47 tokens per session scan A 46afd7929bd0
make-the-next-failure-loud is a skill published in the GitHub repository everywan-dev/claude-code-engineering (2 stars, last pushed 15d ago), licensed Apache-2.0. It adds 47 tokens to every session and 1,163 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
claude-project-manifest
Creates annotated bibliography-style manifests for Claude projects, tracking files, conversation threads, and relationships with unique IDs and annotations. Use when documenting project contents, creating file inventories, tracking conversation history, or building navigable knowledge maps.
proofpress
Preserve or inspect decision history for Markdown and static HTML knowledge artifacts with Proofpress. Use when creating or accepting a meaningful revision to an ADR, design doc, PRD, README, strategy note, portable .md artifact, or static .html/.htm artifact in a configured repository, or when receiving a file…
llm-wiki
Maintain a personal team knowledge base using the LLM Wiki pattern — incremental ingest, query, and lint operations on a layered wiki architecture.
PBE Extractor
Extract invariant principles from any text — find the ideas that survive rephrasing.
Principle Synthesizer
Synthesize invariant principles from 3+ sources — find the core that survives across all expressions.
book-to-skill
Use when convert technical books and documents (PDF, EPUB, DOCX, HTML, Markdown, RTF, MOBI) into structured agent skills with frameworks, mental models, chapter references, and decision rules. Includes full extraction pipeline. Use when the user wants to turn a book or document collection into a reusable agent skill…