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/root-cause-analysis-firstnpx skills add everywan-dev/claude-code-engineering --skill root-cause-analysis-firstgit clone --depth 1 https://github.com/everywan-dev/claude-code-engineeringWhat 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 | $0.00048 | $0.01414 |
| Opus 5 | $0.00024 | $0.00707 |
| Sonnet 5 | $0.00010 | $0.00283 |
| Haiku 4.5 | $0.00005 | $0.00141 |
Grade A, and why
root-cause-analysis-first 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 yesterday.
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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Root cause analysis first
Before you touch anything, finish this sentence with a mechanism:
This happens because ______.
If the honest ending is "I don't know, but this makes it go away", you do not have a fix. You have a change that coincides with the symptom disappearing, which is a different and much worse thing: the failure is still there, now without its warning light.
When to use this
- A service crashes, restarts, hangs, or returns the wrong thing
- A test is flaky
- Someone says "just bump the timeout / add a retry / restart it nightly"
- You are on your second attempted fix for the same symptom
The failure this prevents
A reverse proxy was restarting every 45 seconds. Three explanations were put forward, each plausible, each acted on:
- Memory — it must be getting killed for using too much.
- A startup timer — something must be tearing it down before it settles.
- The restart policy — the policy must be misconfigured.
All three were wrong. Not unlucky: wrong in the same way. Every one of them started from a suspect and went looking for evidence that fit. Evidence that fits is always available.
The cause showed up only when someone stopped proposing and started collecting: follow the process tree upward from the thing being killed, and keep following it. It ended at a container that was talking to the runtime socket and stopping the proxy on a loop. Nothing to do with memory, timers, or policy — and nothing that any of those three lines of investigation could ever have found, however long they ran.
The lesson is not "look at process trees". It is that a hypothesis you are trying to confirm cannot be disproved by you. You have to go at it the other way round.
The procedure
1. Collect facts before you allow yourself a theory. Timestamps, exit codes, signal numbers, the last 200 log lines before the event and not after, what changed in the last 24 hours, who else has access.
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.
- yesterday First seen · 132 lines · 48 tokens per session scan A 87965471ae18
root-cause-analysis-first is a skill published in the GitHub repository everywan-dev/claude-code-engineering (2 stars, last pushed 13d ago), licensed Apache-2.0. It adds 48 tokens to every session and 1,414 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.
Principle Synthesizer
Synthesize invariant principles from 3+ sources — find the core that survives across all expressions.
PBE Extractor
Extract invariant principles from any text — find the ideas that survive rephrasing.
golden-rss
Use when testing the rss golden build.