Oldhand Rca

Finds the evidence-backed root cause of a bug, incident or unexpected behaviour. Pins the symptom to a real failing case, confirms the account, deployed commit and config first, reads the failing run's own record, reproduces with the real stored input, clears or convicts each suspect with a cheap read-only probe, names the class of bug and every sibling site, defines a failed set and a regression set for replay, and spawns 2-3 read-only sub-agents to try to refute the chosen cause. Use when the user says "root-cause this", "find the root cause", "find out what went wrong", "why did this run fa

9 stars 2 forksDevOps & Cloud Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add berwinsingh/oldhand

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add berwinsingh/oldhand --skill oldhand-rca
Manual install
git clone --depth 1 https://github.com/berwinsingh/oldhand.git /tmp/oldhand
mkdir -p ~/.claude/skills
cp -r /tmp/oldhand/skills/oldhand-rca ~/.claude/skills/oldhand-rca

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# oldhand-rca

Evidence first. The obvious suspect (the model, a flag, the last deploy) is often innocent, and one
symptom often hides several faults. This stage proves the cause from the failing run's own records and
cheap probes, names the whole class, and lets sub-agents try to break it before anyone builds a fix.

## What the user typed

`$ARGUMENTS`: the text after the skill name (other hosts: the user's message), or the conversation.

## Reads and writes

- Reads: `contract.md`, `trace.md`, the failing run's records and logs, code, config, deploy state.
- Writes: `.oldhand/<task>/rca.md`; probe scripts, the replay harness, refuter briefs and memos
  under `.oldhand/<task>/rca/` (not a temp dir, so they survive). No fix is built here.

Tool: `python3 "${CLAUDE_SKILL_DIR}/../oldhand/scripts/ledger.py"`, called LEDGER below; run one call
at a time. If that variable is not expanded on your host, use this skill's own folder in its place.
If ledger.py is not at that path, the pack is only partly installed: tell the user to install all
11 skills and stop.

## Step 1: Find the task folder and pin the symptom

Use the task folder the conversation names (`Task folder: <path>`), else the one `LEDGER where` prints;
read contract.md and trace.md. None, or a contract about another request: run the oldhand-contract
steps in short form (2-6 criteria, noted under Open questions as derived assumptions). No trace.md:
Read the full skill on GitHub

Details

Skill name
oldhand-rca
Path
skills/oldhand-rca/SKILL.md
License
MIT
Repo updated
17 November 2026

FAQ

What does the Oldhand Rca skill do?

Finds the evidence-backed root cause of a bug, incident or unexpected behaviour. Pins the symptom to a real failing case, confirms the account, deployed commit and config first, reads the failing run's own record, reproduces with the real stored input, clears or convicts each suspect with a cheap read-only probe, names the class of bug and every sibling site, defines a failed set and a regression set for replay, and spawns 2-3 read-only sub-agents to try to refute the chosen cause. Use when the user says "root-cause this", "find the root cause", "find out what went wrong", "why did this run fa

How do I install the Oldhand Rca skill?

Claude Code plugin: /plugin marketplace add berwinsingh/oldhand. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Oldhand Rca popular?

It lives in berwinsingh/oldhand, which has 9 GitHub stars and 2 forks.

Related skills

Oldhand

9

berwinsingh/oldhand

Conducts non-trivial software work end to end through a chain of stage skills: reads the ticket or prompt, traces the real code path, reuses proven code, makes the smallest correct change, has sub-agents review and QA it in the running app, and lets a computed verdict, not the model, say when it is done. Use when the user asks to implement, build, fix, debug, root-cause, investigate, QA or verify a feature or bug; says "pick up this ticket", "work on ENG-123", "fix this bug", "why is X broken", "plan this first" or "make sure it works end to end"; or pastes a Jira, Linear, Asana, monday.com or

AI, LLMs & Agents

Oldhand Build

9

berwinsingh/oldhand

Implements a planned change the lazy, correct way: reuse what the codebase has, then the standard library, the platform and installed dependencies, and only then the least new code, fixing the whole class of bug at the shared point. Takes a baseline of the repo checks before the first edit, leaves one focused regression check, proves that check guards the fix with a mutation run (mutate.py), and compares the checks with the baseline. Records unit, integration and mutation results in the Oldhand ledger and writes build.md in the task's .oldhand folder. Use when the user says "implement the plan

Software Development

Oldhand Contract

9

berwinsingh/oldhand

Turns a ticket, document or prompt into a work contract with numbered acceptance criteria (AC) and regression criteria (R), then opens the task's .oldhand folder and ledger that every later Oldhand stage reads. Reads the whole tracker item (description, every comment, attachments, linked work), keeps the user's assumptions, changed requirements, constraints, partial work and requested proof, and records which remote actions are authorized. Use when the user says "here is the spec", "scope this", "write the acceptance criteria" or "what exactly is being asked". Not for one-line edits, typo fixe

Marketing, Sales & Business

Game Server Stability Optimization

5

dungnotnull/game-server-stability-optimization-agent-skill

Dedicated Game Server Stability & Performance Optimization — Expert Game Server Reliability & Performance Engineering analysis harness. Use this skill whenever the user mentions game servers, multiplayer infrastructure, server optimization, dedicated game hosting, cloud gaming architecture, server scaling, load balancing for games, DDOS mitigation for games, game server monitoring, observability for game systems, tick rate optimization, game server reliability, high availability game infrastructure, multiplayer backend architecture, game server capacity planning, or any game infrastructure rel

DevOps & Cloud

Evm Deployment

9

sablier-labs/agent-skills

Deploy Sablier EVM contracts (Utils, Flow, Lockup, Airdrops, Bob) with full workflow automation. This skill should be used when the user asks to "deploy", "deploy protocol", "deploy to chain", or mentions deployment-related tasks. Handles contract deployment, explorer verification, SDK updates, and initial setup through Init scripts.

DevOps & Cloud

Red Tide Algal Bloom Monitoring

5

dungnotnull/red-tide-algal-bloom-monitoring-agent-skill

Red Tide (Harmful Algal Bloom) Monitoring & Early Warning - HAB Monitoring & Aquaculture Safety analysis & decision-support harness. Use this skill whenever the user asks about red tide, harmful algal blooms, HAB monitoring, aquaculture safety, marine water quality, algal toxin detection, shellfish safety, marine biological monitoring, satellite chlorophyll analysis, coastal water management, or needs analysis of marine bloom events. This includes queries about bloom detection, toxin risk assessment, aquaculture impact, early warning systems, environmental triggers, species identification, or

DevOps & Cloud

Browse the most popular Claude skills, all devops & cloud skills, or write your own with the skills generator.