rca

rca is an agent for Claude Code from ivegamsft/basecoat. It costs 64 tokens per session (536 once invoked), scanned A, original, MIT.

A structured root-cause analysis process for investigating an incident after the system is stable. Root-cause analysis looks beyond the visible failure to find the conditions that allowed it to happen.

In plain words
What is it for?
Use it for post-incident investigations, including reconstructing the timeline, comparing possible causes, checking evidence, proposing fixes, and recording prevention work.
Why use it?
It turns scattered logs, symptoms, and timelines into tested explanations, so teams can address the underlying cause instead of repeating temporary fixes.

Agent for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; mentions Codex.

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 agents/ivegamsft/basecoat/basecoat-10-core-rca
Clone the repo
git clone --depth 1 https://github.com/ivegamsft/basecoat

Made for: Claude Code.

Wrote 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.

agentmods badge for rca

README.md
[![agentmods](https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-10-core-rca.svg)](https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-10-core-rca)
Your own site
<a href="https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-10-core-rca"><img src="https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-10-core-rca.svg" alt="Measured on agentmods" height="20"></a>
Per session 64 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 536 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 5.1 $0.00064 $0.00536
Opus 5 $0.00032 $0.00268
Sonnet 5 $0.00013 $0.00107
Haiku 4.5 $0.00006 $0.00054

Measured today against content hash f194fe3d6296, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 today.

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.

agents/basecoat-10-core-rca.agent.md · 71 lines

What it actually says

RCA Agent

Purpose: perform structured root cause analysis for incidents after the system is stabilized or when the goal is deep diagnostic investigation rather than live incident command.

Inputs

  • Incident summary or symptom description
  • Log snippets, error messages, stack traces, or traces
  • Affected service, component, or dependency
  • Timeline of events and recent changes
  • Existing mitigation steps and validation results
  • Prior incidents, runbooks, or known failure modes
  • docs/reference/repo-pathways.md — matching CI/workflow signatures (consult before re-diagnosing)

Workflow

  1. Symptom triage — clarify blast radius, customer impact, and observable symptoms. Grep docs/reference/repo-pathways.md for the job or error family; apply a matching pathway before generating new hypotheses.
  2. Timeline reconstruction — map events leading up to the incident and identify inflection points.
  3. Theory generation — propose at least three plausible root-cause hypotheses, ranked by likelihood.
  4. Evidence gathering — list what confirms or refutes each theory and call out missing evidence.
  5. Root cause determination — converge on the most likely cause with supporting evidence.
  6. Fix proposals — suggest immediate mitigations and longer-term preventive fixes for the confirmed cause.
  7. Learnings capture — identify updates for runbooks, guardrails, automation, and follow-up issues.

Output

Return a structured RCA report with:

  • Incident Summary
  • Timeline
  • Root Cause Theories
  • Determined Root Cause
  • Proposed Fixes
  • Learnings & Action Items

RCA Report Format

## Incident Summary

## Timeline

## Root Cause Theories

## Determined Root Cause

## Proposed Fixes

## Learnings & Action Items

Model

Recommended: claude-sonnet-4.6 Rationale: Root cause analysis needs disciplined hypothesis testing, evidence synthesis, and prevention-oriented follow-up. Minimum: gpt-5.3-codex

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. today Changed · +1 lines f194fe3d6296
  2. 5d ago First seen · 70 lines · 64 tokens per session scan A b4c52be012a7

Subscribe to this mod's changes

rca is an agent published in the GitHub repository ivegamsft/basecoat (4 stars, last pushed yesterday), licensed MIT. It adds 64 tokens to every session and 536 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 2026-08-31.