uces: Instructions file for Claude Code

CLAUDE.md

uces CLAUDE.md is an instructions file for Claude Code from eticmedya/uces. It costs 990 tokens per session, scanned A, original, MIT.

Project-wide instructions for UCES, a system that routes coding requests to modules such as UI, API, mobile, debugging, security, and deployment. It also defines patterns that are forbidden and conditions for completion.

In plain words
What is it for?
Routing feature requests, implementing UI or backend work, debugging, handling security-related tasks, and checking that integrations and user-visible states are complete.
Why use it?
They make agents choose a relevant work area and reject incomplete implementations, placeholder data, weak typing, and silent failures.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths.

This is eticmedya/uces's own configuration. It tells Claude Code how to work on uces 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 uces configures →

Reuse

Borrowing it

Nothing to install: this file belongs to eticmedya/uces. 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/eticmedya/uces/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/eticmedya/uces

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 uces CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/eticmedya/uces/claude-md/github.svg)](https://agentmods.dev/instructions/eticmedya/uces/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/eticmedya/uces/claude-md"><img src="https://agentmods.dev/badge/instructions/eticmedya/uces/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for uces CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/eticmedya/uces/claude-md"><img src="https://agentmods.dev/badge/instructions/eticmedya/uces/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 990 This file is loaded in full into every session.
When invoked 990 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00990 $0.00990
Opus 5.5 $0.00396 $0.00396
Sonnet 5.5 $0.00198 $0.00198
Haiku 4.5 $0.00099 $0.00099

Measured 2mo ago against content hash b4c1575cf405, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

uces CLAUDE.md 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 2mo 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.md · 171 lines

How it starts

The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UCES Core Directives

Reference: ~/.claude/CONVENTIONS.md for detailed standards


Intelligent Routing

Route requests to the appropriate skill module:

Keywords Module
component, page, UI, form, button, modal, React, Next.js, Tailwind, styling ui
API, endpoint, route, database, REST, GraphQL, webhook, server, Supabase api
mobile, Expo, React Native, NativeWind, iOS, Android, app native
bug, error, fix, debug, broken, failing, test, spec debug
auth, login, security, permission, OWASP, encryption, JWT guard
plan, design, architecture, PRD, spec, requirements, system architect
analytics, metrics, query, data, dashboard, report, KPI data
deploy, CI/CD, Docker, pipeline, infrastructure, DevOps devops

Zero-Tolerance Enforcement

Blocked Patterns

  • Placeholder data → Connect real sources
  • Deferred implementations → Complete now
  • Stub handlers → Full logic required
  • Partial state handling → All states mandatory
  • Loose typing → Strict TypeScript
  • Silent failures → User feedback required

Completion Criteria

[✓] Integrated with actual data sources
[✓] States covered: loading, error, empty, success
[✓] Errors surface to user appropriately
[✓] TypeScript: zero errors
[✓] Production-ready quality

Verification Protocol

Before marking complete:

  1. Execute validation:

    npx tsc --noEmit    # Must pass
    npm test            # Must pass
    
  2. UI deliverables: Describe rendered state

  3. API deliverables: Show response structure

  4. Uncertainty: Explicitly state unknowns

Communication standards:

  • Never claim unverified success
  • Surface all warnings/errors
  • Ask rather than assume

Implementation Templates

API Endpoint

// 1. Authentication
const session = await getSession()
if (!session) return unauthorized()

// 2. Input validation
const validated = Schema.safeParse(input)
if (!validated.success) return badRequest(validated.error)

// 3. Authorization
if (resource.ownerId !== session.userId) return forbidden()

// 4. Execution with error handling
try {
  const result = await execute(validated.data)
  return success(result)
} catch (e) {
  log.error(e)
  return serverError()
}

Read the full file on GitHub · 171 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. 2mo ago First seen · 171 lines · 990 tokens per session scan A b4c1575cf405

Subscribe to this mod's changes

uces CLAUDE.md is an instructions file published in the GitHub repository eticmedya/uces (104 stars, last pushed 9mo ago), licensed MIT. It adds 990 tokens to every session, about $0.0040 per session on Opus 5.5. 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

uces CLAUDE.md compared with instructions from other repositories

uces CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
uces CLAUDE.mdeticmedya/ucesInstructions file1049mo agoMITA990Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode