accuracy

A careful coding workflow that prioritises correctness over saving time or conversation space. It is intended for agents implementing code, rather than agents reviewing someone else's code.

In plain words
What is it for?
Use it for implementation tasks where correctness matters, while keeping planning and progress in the conversation and creating only the code files the task requires.
Why use it?
Coding changes can cause rework when the requirements, affected files, or results are not checked carefully. This workflow calls for extensive context gathering, planning, verification, and a final challenge of the proposed work.

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

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,066 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 $0.01066
Opus 5 $0.00000 $0.00533
Sonnet 5 $0.00000 $0.00213
Haiku 4.5 $0.00000 $0.00107

Measured 2d ago against content hash 0e4bffbfb45e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

accuracy 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 2d 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/accuracy/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Accuracy — Solo High-Accuracy Coding Mode

Scope: This skill is for CODING/IMPLEMENTATION agents only. It is NOT for review agents. If you are reviewing someone else's work, use the review skill instead.

This workflow trades tokens for correctness. It's designed for contexts where usage is free or low-cost, so the strategy is: invest heavily in context-gathering and planning, verify at every gate, and red-team before finishing — to minimize rework rather than to save prompts.

File Creation Rules

  • When creating files in .switchboard/, always use IsArtifact: false to prevent path validation errors.

No-Artifact Rule

  • /accuracy is a solo, in-conversation workflow. Do NOT write out artifacts to disk as part of execution — no task.md, no plan files, no Red Team Findings file, no progress logs. All progress tracking and review output belongs in your reply to the user; planning itself is internal (see Step 3) and is NOT presented as a plan-in-reply. The only files you create or modify are the actual code files required by the task itself.

Quick Reference

  • Valid Actions: None (solo workflow, no cross-agent delegation)

Steps

  1. Start — Activate accuracy mode via the /accuracy command. This workflow operates without MCP tool dependencies.

  2. Deep Context Gathering (invest time here to avoid rework):

    • MUST read ALL files that will be modified or depend on changes.
    • MUST read existing tests, types, and interfaces related to the task.
    • MUST identify every dependency and side-effect BEFORE writing any code.
    • WHY: Missing context causes mistakes. Mistakes cause rework. Front-loading context is cheaper than fixing bugs later.
    • Mark Phase 1 complete in your reply (a brief checklist is fine) or via the Kanban UI if available. Do NOT create any tracking files on disk.
  3. Internal Planning (think before you code, but do NOT present a plan-in-reply):

    • MUST map dependencies between changes internally — which must happen first?
    • MUST identify risks: what could break? What edge cases exist?
    • DESTRUCTION CHECK: If deleting files, MUST run grep_search to confirm nothing depends on them.
    • RULE: Spend more time thinking. A thought-through approach that prevents a rework cycle is worth far more than the tokens it costs.
    • Do NOT produce a plan-in-reply or present a plan for approval — proceed directly to Step 4 (implementation).
    • Do NOT write a plan file to disk — plan files are the domain of /improve-plan, not /accuracy (enforced by the No-Artifact Rule above).

Read the full file on GitHub · 65 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. 2d ago First seen · 65 lines · 0 tokens per session scan A 0e4bffbfb45e

Subscribe to this mod's changes

accuracy is a skill published in the GitHub repository TentacleOpera/switchboard (213 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,066 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

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

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens