What is career-ops-ui GEMINI.md?

A small instruction file that points Gemini CLI to the project’s main instructions in CLAUDE.md. Gemini CLI is a command-line tool used to work on the code, while the deployed application runs independently of that tool.

Starting Gemini CLI sessions in career-ops-ui, directing the agent to the correct project guidance, and documenting Gemini-specific development notes and tests.

It keeps Gemini sessions aligned with the project’s shared rules without duplicating those rules in multiple files.

career-ops-ui GEMINI.md — Instructions file for Gemini CLI by Fighter90: A small instruction file that points Gemini CLI to…

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/gemini-md

Clone the repo

git clone --depth 1 https://github.com/Fighter90/career-ops-ui

Made for: Gemini CLI.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/fighter90/career-ops-ui/gemini-md.svg)](https://agentmods.dev/instructions/fighter90/career-ops-ui/gemini-md)

Your own site

<a href="https://agentmods.dev/instructions/fighter90/career-ops-ui/gemini-md"><img src="https://agentmods.dev/badge/instructions/fighter90/career-ops-ui/gemini-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 656 This file is loaded in full into every session.

When invoked 656 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.

Model	Per session	Once invoked
Fable 5	$0.00656	$0.00656
Opus 5	$0.00328	$0.00328
Sonnet 5	$0.00131	$0.00131
Haiku 4.5	$0.00066	$0.00066

Measured 4d ago against content hash 0b5a358dfa3c, 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 GEMINI.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 4d 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.

GEMINI.md · 35 lines

How it starts

The opening of the file, as written. The whole thing — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.

career-ops-ui — Agent Instructions (Gemini CLI shim)

Gemini CLI auto-loads this file at session start. The actual project-level instructions, hard rules, conventions, and SDD pipeline live in CLAUDE.md — everything there applies to Gemini equally. This file is a thin pointer so Gemini-driven sessions get the same orientation as Claude Code or Codex sessions.

Read CLAUDE.md next.

Why a shim

The parent career-ops project supports multiple CLIs (Claude Code, Codex, Gemini, OpenCode) via the Open Agent Skill standard. This UI sub-project adopts the same convention: one source of truth (CLAUDE.md) plus thin shims (AGENTS.md for Codex, this file for Gemini).

Gemini-specific notes

The UI itself is CLI-agnostic at runtime. The Gemini CLI is only relevant during development inside this repo. The deployed UI runs as a regular Node ≥18 process and works regardless of which CLI authored the code.
npm run test:e2e:browser (Playwright smoke) drives a real Chromium against the in-process server. Resolves Playwright via the parent project's node_modules — no new dependency in web-ui/.
The SDD pipeline (docs/sdd/SDD-GUIDE.md) is described in CLI-agnostic terms; Gemini users follow the same discuss → spec → plan → execute → verify → review loop, manually creating Markdown artifacts under .planning/phases/P-NN-<slug>/ if the GSD slash-commands aren't available.
Live LLM execution from /api/evaluate, /api/deep, /api/mode/:slug works with either ANTHROPIC_API_KEY or GEMINI_API_KEY set in the parent project's .env. Anthropic is preferred when both are present (better long-form structured output).

Hard rules — do NOT violate

(See CLAUDE.md for the complete list with rationale.)

Never edit outside web-ui/. The parent career-ops project owns cv.md, config/, modes/, data/, reports/, etc.
Never weaken security headers (CSP, X-Frame-Options, etc.).
Never bypass isValidJobUrl() (SSRF guard) or stripDangerousMarkdown() (XSS guard).
Never commit .env. Never log secrets.
Tests must be CI-isolated.
No git --no-verify, no --force push, no git reset --hard without explicit user approval.

Read the full file on GitHub · 35 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.

4d ago First seen · 35 lines · 656 tokens per session scan A 0b5a358dfa3c

Subscribe to this mod's changes

career-ops-ui GEMINI.md is an instructions file published in the GitHub repository Fighter90/career-ops-ui (58 stars, last pushed 4d ago), licensed MIT. It adds 656 tokens to every session, about $0.0033 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.

ashby career-ops claude-code express greenhouse-api hh-ru

payload AGENTS.md

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

Claude Code 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

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

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

igniter-js GEMINI.md

Gemini CLI instructions for felipebarcelospro/igniter-js, covering 1. identity and profile, 2. about the igniter.js monorepo, 3. personality and communication, 4. lia's core responsibilities (the 4 pillars) and 5. technical guidelines and methodology.

felipebarcelospro/igniter-js · 9,239 tokens

igniter-js writing-style.instructions.md

Instructions for felipebarcelospro/igniter-js, covering ✍️ unified documentation style guide (for llms & authors), 🎯 core style principles (applies to all documentation), 📘 documentation (docs): writing style, installation and quick start.

felipebarcelospro/igniter-js · 3,722 tokens