tuning

tuning is a skill for Claude Code, Codex from TentacleOpera/switchboard. It costs 0 tokens per session (531 once invoked), scanned A, original, MIT.

A method for finding recurring problems in completed project plans and saving them as reusable insight documents. It groups similar issues, such as missing error handling or untested assumptions, and can suggest updates to team rules.

In plain words
What is it for?
Use it to review completed plans, identify repeated problem patterns, update existing insights, and propose changes to governance files such as team instruction documents.
Why use it?
It prevents the same planning mistakes from being rediscovered in later work and keeps evidence connected to the plans where it appeared.

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/tentacleopera/switchboard/tuning
Any agent
npx skills add TentacleOpera/switchboard --skill tuning
Clone the repo
git clone --depth 1 https://github.com/TentacleOpera/switchboard

Made for: Claude Code, Codex.

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 tuning

README.md
[![agentmods](https://agentmods.dev/badge/skills/tentacleopera/switchboard/tuning.svg)](https://agentmods.dev/skills/tentacleopera/switchboard/tuning)
Your own site
<a href="https://agentmods.dev/skills/tentacleopera/switchboard/tuning"><img src="https://agentmods.dev/badge/skills/tentacleopera/switchboard/tuning.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 531 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 $0.00000 $0.00531
Opus 5 $0.00000 $0.00266
Sonnet 5 $0.00000 $0.00106
Haiku 4.5 $0.00000 $0.00053

Measured 4d ago against content hash f7ff969befcc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tuning 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.

.agents/protocols/tuning/SKILL.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tuning Skill

Purpose

Extract recurring problem patterns from adversarial review sections in completed/reviewed plans, store them as individual insight documents, and propose governance file updates.

Modes

Extract Mode

Receive a list of plan file paths and scan each for adversarial review sections ("Stage 1 — Grumpy Adversarial Findings" and "Stage 2 — Balanced Synthesis"). Cluster recurring problem patterns across plans and create individual insight .md files in {workspaceRoot}/.switchboard/insights/.

Clustering criteria:

  • Same problem category (e.g., missing error handling, race conditions, prompt-design flaws, unvalidated assumptions)
  • Same severity level (recurring vs critical vs minor)
  • Same governance target (CONSTITUTION.md vs AGENTS.md vs CLAUDE.md)

Deduplication: Before creating a new insight, check existing insights in .switchboard/insights/. If an existing insight covers the same pattern (same category AND similar description), append new evidence to it instead of creating a duplicate. When appending, update the Source Plans list and add new evidence entries.

Governance Mode

Read all insight files in {workspaceRoot}/.switchboard/insights/ with status open. Review the insights and propose specific edits to governance files (CONSTITUTION.md, AGENTS.md, CLAUDE.md) to address the recurring patterns. Present proposed changes as diffs.

Insight File Template

# [Insight Title]

## Metadata
**Created:** [date]
**Source Plans:** [list of plan filenames that contributed this pattern]
**Severity:** [recurring | critical | minor]
**Status:** [open | applied | dismissed]

## Problem Pattern
[Description of the recurring issue observed across plans]

## Evidence
- **[plan-filename.md]**: [specific quote or paraphrase from the adversarial section]
- **[plan-filename.md]**: [specific quote or paraphrase]

## Recommendation
[Suggested rule or invariant to add to governance files]

## Suggested Governance Target
[CONSTITUTION.md | AGENTS.md | CLAUDE.md | .cursor/rules/]

Read the full file on GitHub · 57 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. 4d ago First seen · 57 lines · 0 tokens per session scan A f7ff969befcc

Subscribe to this mod's changes

tuning is a skill published in the GitHub repository TentacleOpera/switchboard (213 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 531 tokens. 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