working-to-standard

working-to-standard is a skill for Claude Code, Codex from theam/facility. It costs 39 tokens per session (445 once invoked), scanned A, original, Apache-2.0.

A repository-specific set of instructions for applying the rules in STANDARD.md while changing product code.

In plain words
What is it for?
It guides planning, editing, verification, reviewer-checklist use, side-effect handling, and reporting for behavior-changing work.
Why use it?
It helps keep implementation decisions aligned with the project's domain rules, existing patterns, validation practices, and required review checks.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions subagents.

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/theam/facility/working-to-standard
Any agent
npx skills add theam/facility --skill working-to-standard
Clone the repo
git clone --depth 1 https://github.com/theam/facility

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 working-to-standard

README.md
[![agentmods](https://agentmods.dev/badge/skills/theam/facility/working-to-standard.svg)](https://agentmods.dev/skills/theam/facility/working-to-standard)
Your own site
<a href="https://agentmods.dev/skills/theam/facility/working-to-standard"><img src="https://agentmods.dev/badge/skills/theam/facility/working-to-standard.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 445 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 $0.00039 $0.00445
Opus 5 $0.00019 $0.00222
Sonnet 5 $0.00008 $0.00089
Haiku 4.5 $0.00004 $0.00044

Measured 6d ago against content hash 605a6617fbda, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

working-to-standard 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 6d 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.

packages/cli/templates/claude/skills/working-to-standard/SKILL.md · 46 lines

What it actually says

Working to standard

STANDARD.md is the contract; this skill is how it's applied while the work is happening, not checked after the fact.

Before editing

  1. Read STANDARD.md, including the module sections between the facility:modules markers — they carry domain rules (data, analytics, design, AI exposure) that change what "done" means.
  2. Name the user-facing outcome, the affected boundaries, the invariants that must hold, and the rollback surface. If you can't, the task isn't clear enough to edit yet — ask the one question that unblocks it.
  3. Find the local pattern first. The repo's existing shape beats the general best practice; new abstractions need to remove real complexity.

While editing

  • Deliver the WHOLE request as the smallest coherent change — no drive-by refactors, no "phase 1" unless phasing was requested.
  • Keep side effects at the edges and visible: network, database, time, randomness, file system, model calls.
  • Validate input at trust boundaries with the existing schema/parsing patterns; make invalid states hard to represent.
  • When you touch a domain with a reviewer subagent in .claude/agents/, apply its checklist as you go — cheaper than failing its review later.

Verifying

Run the lightest useful checks first, escalate by risk, per the verification ladder in STANDARD.md. node guards/run.mjs is always cheap and always relevant. A check you cannot run is reported by name with the reason — never claimed.

Reporting done

One concise summary: what changed and why, the checks you ran with their results, and any genuinely out-of-scope follow-ups. Walk the completion checklist in STANDARD.md before saying done; an unmet item is either fixed or explicitly reported, never silent.

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. 6d ago First seen · 46 lines · 39 tokens per session scan A 605a6617fbda

Subscribe to this mod's changes

working-to-standard is a skill published in the GitHub repository theam/facility (58 stars, last pushed yesterday), licensed Apache-2.0. It adds 39 tokens to every session and 445 once invoked, about $0.0002 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

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens