coding-with-ai-lab: Skill for Claude Code

.claude/skills/update-claude-files/SKILL.md

project:update-claude-files is a skill for Claude Code from atra-consulting/coding-with-ai-lab. It costs 71 tokens per session (5,595 once invoked), scanned A, original, MIT.

A documentation-maintenance skill for Claude project files, including agent instructions, specifications, and CLAUDE.md.

In plain words
What is it for?
Use it after features, schema changes, or infrastructure changes to update existing documents and create or remove documents when the code clearly requires it.
Why use it?
It keeps project documentation aligned with code changes so instructions and specifications do not become outdated.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is atra-consulting/coding-with-ai-lab's own configuration. It tells Claude Code how to work on coding-with-ai-lab itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything coding-with-ai-lab configures →

Reuse

Borrowing it

Nothing to install: this file belongs to atra-consulting/coding-with-ai-lab. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/atra-consulting/coding-with-ai-lab/main/.claude/skills/update-claude-files/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/atra-consulting/coding-with-ai-lab

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 project:update-claude-files

README.md
[![agentmods](https://agentmods.dev/badge/skills/atra-consulting/coding-with-ai-lab/update-claude-files.svg)](https://agentmods.dev/skills/atra-consulting/coding-with-ai-lab/update-claude-files)
Your own site
<a href="https://agentmods.dev/skills/atra-consulting/coding-with-ai-lab/update-claude-files"><img src="https://agentmods.dev/badge/skills/atra-consulting/coding-with-ai-lab/update-claude-files.svg" alt="Measured on agentmods" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,595 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high System Prompt Leakage · line 30
    Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.
    Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
  • high Tool Misuse · line 117
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
How audits are shown
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 $0.00071 $0.05595
Opus 5 $0.00036 $0.02797
Sonnet 5 $0.00014 $0.01119
Haiku 4.5 $0.00007 $0.00560

Measured 7d ago against content hash e1210c78e5b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

project:update-claude-files 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 7d 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.

.claude/skills/update-claude-files/SKILL.md · 400 lines

How it starts

The opening of the file, as written. The whole thing — 400 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Update Claude Files

You keep this project's docs in sync with its code. Targets: .claude/agents/*.md, docs/specs/*.md (the SPECS*.md set plus DOMAIN.md), and CLAUDE.md.

This project: Node/Express/TypeScript backend (backend/) + Angular 21 frontend (frontend/), Drizzle ORM over libSQL/SQLite. Curated spec set. Curated agent roster. Default: you update existing docs in place. You may create a missing spec or agent file, or delete an obsolete one, but only when the code clearly demands it — see Create & Delete Docs below.

Writing Style

Short and brief. Short sentences. Simple words non-native speakers understand. No passive voice. Use sentence fragments. Match each doc's existing tone — specs mix German domain terms with English prose. Keep German domain terms (Firma, Person, Chance, …).

FILE PATH DISPLAY RULE

Show full absolute paths. Get the root with pwd and prepend it. This lets users Command-click paths in the terminal.

HOW TO ASK THE USER FOR DECISIONS

Use the AskUserQuestion tool for every prompt. Never print a question as prose and wait. Never read stdin. Embedded mode never prompts — see PHASE 0.

Preserve Human-Authored Content

Specs and agents are hand-written. Update only the facts the code changes made stale. Keep manual sections, domain language, and structure. Never replace careful prose with generic phrasing. Prune a line only when the source clearly made it wrong (a removed route, a renamed column, a deleted entity).

Create & Delete Docs

Default: update an existing file. Create or delete only when the code leaves no honest alternative.

Create a spec when a code area exists but no spec file covers it. Bootstrap case: if docs/specs/ is empty or missing but source code exists, author the full spec set from scratch by reading the code — SPECS.md (the index), DOMAIN.md, and one SPECS-*.md per area the code has. Use the same file names this skill already expects (Step 3.1).

Create an agent only when special_instructions asks for it explicitly. Never invent an agent on your own.

Read the full file on GitHub · 400 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. 7d ago First seen · 400 lines · 71 tokens per session scan A e1210c78e5b9

Subscribe to this mod's changes

project:update-claude-files is a skill published in the GitHub repository atra-consulting/coding-with-ai-lab (5 stars, last pushed yesterday), licensed MIT. It adds 71 tokens to every session and 5,595 once invoked, about $0.0004 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.

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-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

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