rca

An evidence-based investigation into the underlying cause of a software defect.

In plain words
What is it for?
It helps recheck assumptions, compare possible explanations, inspect logs or measurements, reproduce evidence, and record a confirmed cause in the task specification.
Why use it?
It prevents a plausible guess from being treated as the cause before the problem is checked against real data.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/rakovi4/continue-framework/rca
Any agent
npx skills add rakovi4/continue-framework --skill rca
Clone the repo
git clone --depth 1 https://github.com/rakovi4/continue-framework

Made for: Claude Code, Codex.

Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,050 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00057 $0.01050
Opus 5 $0.00028 $0.00525
Sonnet 5 $0.00011 $0.00210
Haiku 4.5 $0.00006 $0.00105

Measured 3d ago against content hash cdbc35fa51f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rca 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 3d 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.

.claude/skills/rca/SKILL.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/rca - Root Cause Analysis

Find the real cause of a defect from evidence, not speculation. The deliverable is a cause you have confirmed against real data — logs, test runs, query plans, measurements you actually pulled — recorded in the task spec.md. Producing a plausible-sounding story is the failure mode this skill exists to prevent: a narrative that was never checked against data is a guess, even when it reads like a conclusion.

Input

  • target (optional): bugfix task number/slug, or a free-text symptom. If absent, infer from the current task or conversation.
  • evidence sources (optional): credentials or paths for authoritative data (CI API, log locations, a reproducible environment). When provided, use them — do not substitute a guess for data you could fetch.

Core Principle

Every prior claim is a hypothesis until you re-verify it here — including claims already written in spec.md, an earlier RCA attempt, a code comment, or this conversation. Carrying a prior hypothesis forward as established fact is the exact failure this skill exists to prevent. Re-derive each claim from primary evidence, or mark it unverified. Distinguish MEASURED (you observed it directly) from REASONED (you inferred it from code plus rules) on every statement, and never present REASONED as MEASURED.

Workflow

  1. State the symptom precisely. Pull the exact observable from its authoritative source — the test report, the log line, the failing assertion message — with exact values, units, and frequency, not a paraphrase. For an intermittent failure, get the real pass/fail count and the measured values on both sides of the boundary. Quote the source. Confirm which value the assertion actually checks (it is often not the one a summary reports).

  2. Audit prior assumptions. List every claim the existing write-up, prior RCA, comments, or conversation treats as known. For each, record a status — verified (with evidence), refuted (with evidence), or unverified — and reuse no prior conclusion you have not personally re-confirmed.

Read the full file on GitHub · 51 lines

Changes

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.

  1. 3d ago First seen · 51 lines · 57 tokens per session scan A cdbc35fa51f3

Subscribe to this mod's changes

rca is a skill published in the GitHub repository rakovi4/continue-framework (50 stars, last pushed 6d ago), licensed MIT. It adds 57 tokens to every session and 1,050 once invoked, about $0.0003 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens