agentmods.dev

career-ops-ui copilot-instructions.md

Project instructions for GitHub Copilot when working on the career-ops-ui job-search application. They summarize the app's server, browser interface, tests, supported languages, and required security and coding practices.

In plain words
What is it for?
Use them when asking Copilot to modify the Express server, vanilla JavaScript interface, localization files, routes, or tests in career-ops-ui.
Why use it?
They give Copilot the repository context and rules needed to make compatible changes. This helps preserve existing test coverage, locale support, file conventions, and the app's loopback-only and no-telemetry setup.

Instructions file for GitHub Copilot

58 3d ago A scan 1,409 tokens original MIT
View the source file Fighter90/career-ops-ui
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 instructions/fighter90/career-ops-ui/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/Fighter90/career-ops-ui

Made for: GitHub Copilot.

Per session 1,409 This file is loaded in full into every session.
When invoked 1,409 The same file — it is already loaded in full.
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 $0.01409 $0.01409
Opus 5 $0.00705 $0.00705
Sonnet 5 $0.00282 $0.00282
Haiku 4.5 $0.00141 $0.00141

Measured 3d ago against content hash 054190cf54d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

career-ops-ui copilot-instructions.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 3d 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.

.github/copilot-instructions.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub Copilot — career-ops-ui

GitHub Copilot auto-loads this file when working in this repo. The full project-level instructions, hard rules, conventions, and SDD pipeline live in CLAUDE.md. Everything there applies to Copilot equally. This file is the bite-sized version for the chat sidebar.

Snapshot

career-ops-ui is an Express + vanilla-JS SPA on top of the Fighter90/career-ops job-search pipeline. Single-tenant, loopback-by-default, no telemetry, no build step.

  • Server: Node ≥ 18, Express 4 + js-yaml + multer. .mjs only (ESM). ~130-LOC orchestrator + 15 route modules under server/lib/routes/.
  • SPA: Vanilla JS, hash-router, no framework, no bundler. Files served as-is from public/.
  • Tests: node --test + Playwright. Baseline at v1.69.0 = 1079 unit / 70 Playwright (smoke+full-cycle+forms+locale-sweep) + 20 smoke E2E + 23 comprehensive E2E. Don't reduce coverage.
  • i18n: 13 locales (en, es, pt-BR, ko, ja, ru, zh-CN, zh-TW, fr, pl, uk, da, ar — ar is RTL). Per-locale DICTs in public/js/lib/locales/i18n-dict.<lang>.js, merged by the i18n-dict.js assembler (I18N-SPLIT v1.60.0); CI canary + the byte-for-byte tests/fixtures/i18n-dict.snapshot.json enforce every key exists in every locale.
  • Scanner sources: each job board is a self-registering adapter in server/lib/sources/<slug>.mjs. Since v1.69.0 (P-14) registry.mjs auto-discovers them at boot via each file's export const meta block — drop a file in, no registry edit. (As of v1.136.0: 79 sources, 74 EN + 5 RU.)
  • Repost detector (v1.83.0): server/lib/detect-reposts.mjs + server/lib/role-matcher.mjs cluster data/scan-history.tsv rows re-listed under different URLs within a window; read-only GET /api/scan/reposts → a 🔁 panel on #/scan. Not a source.

Hard rules (Copilot, don't break these)

  1. Never edit outside web-ui/. Parent career-ops is read-only.
  2. Never load real user data (cv.md, data/applications.md, reports/) into chat context.
  3. Never weaken security headers. CSP excludes 'unsafe-inline'; don't relax frame-ancestors 'none'.
  4. Never bypass isValidJobUrl + safeGet for any outbound HTTP from a user-supplied URL.
  5. Never sanitize CV markdown outside stripDangerousMarkdown.
  6. Never commit .env or any real secret.
  7. Tests must be CI-isolated — no parent dependency, no live network, no port collision.

Read the full file on GitHub · 70 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. 3d ago First seen · 70 lines · 1,409 tokens per session scan A 054190cf54d2

Subscribe to this mod's changes

career-ops-ui copilot-instructions.md is an instructions file published in the GitHub repository Fighter90/career-ops-ui (58 stars, last pushed 3d ago), licensed MIT. It adds 1,409 tokens to every session, about $0.0070 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.

ashbycareer-opsclaude-codeexpressgreenhouse-apihh-ru
Related

Other instructions, from other repositories

payload CLAUDE.md

Instructions for payloadcms/payload, covering claude.md, project structure, key directories, architecture notes and quick start.

payloadcms/payload · 5,127 tokens

payload AGENTS.md

Instructions for payloadcms/payload, a project described as: Payload is the open-source, fullstack Next.js framework, giving you instant backend superpowers. Get a full TypeScript backend and admin panel instantly. Use Payload as a headless CMS or for building powerful applications.

payloadcms/payload · 12 tokens

Claude-Code-Agent-Monitor CLAUDE.md

Instructions for hoangsonww/Claude-Code-Agent-Monitor, covering claude code working guide, project mission, repo map, non-negotiable engineering rules and commands you should know.

hoangsonww/Claude-Code-Agent-Monitor · 1,101 tokens

Claude-Code-Agent-Monitor AGENTS.md

Instructions for hoangsonww/Claude-Code-Agent-Monitor, covering codex project instructions, project intent, priorities, where to work and validation expectations.

hoangsonww/Claude-Code-Agent-Monitor · 653 tokens

mcp-app-typescript-template AGENTS.md

AGENTS.md instructions for pomerium/mcp-app-typescript-template, covering repository guidelines, project overview, development commands, quick start and all available commands.

pomerium/mcp-app-typescript-template · 5,171 tokens

AI-RAG-Assistant-Chatbot AGENTS.md

Instructions for hoangsonww/AI-RAG-Assistant-Chatbot, covering lumina codex guide, repository overview, scope rules, working rules and validation commands.

hoangsonww/AI-RAG-Assistant-Chatbot · 1,038 tokens