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.
npx agentmods add instructions/opgginc/opencode-bar/agents-mdgit clone --depth 1 https://github.com/opgginc/opencode-barWhat 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 | $0.11821 | $0.11821 |
| Opus 5 | $0.05910 | $0.05910 |
| Sonnet 5 | $0.02364 | $0.02364 |
| Haiku 4.5 | $0.01182 | $0.01182 |
Grade A, and why
opencode-bar AGENTS.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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 665 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Important Restriction
- All of comments in code base, commit message, PR content and title should be written in English.
- If you find any Korean text, please translate it to English.
- UI Language
- All user-facing text in the app MUST be in English.
- Default review language: English.
Obey design decisions that specifically decided before by me
- All the decision is speicifed in
@AGENTS-design-decisions.mdfile.
Coding Rules
Branding Guides
- Official Brand:
OpenCode Bar- Don't use mis-capitalized or malformed forms like
Opencode Baror versions without the space (e.g.OpenCodeBar).
- Don't use mis-capitalized or malformed forms like
- File Name:
OpenCode Barif it allows whitespace.OpenCode-Barif it allows dash.opencode-bar(all lowercase) if the environment prefers lowercase file names.opencodebar(all lowercase, no separators) if it doesn't allow whitespace or dashes.
- Bundle ID:
com.copilotmonitor.CopilotMonitor
UI Styling Rules
- No colors for text emphasis: Do NOT use
NSColorattributes like.foregroundColorfor menu items or labels. - DO NOT USE SPACES TO ALIGN TEXT: Don't use spaces like " Words:" to align the spacing.
- Use instead:
- Bold:
NSFont.boldSystemFont(ofSize:)for important text - Underline:
.underlineStyle: NSUnderlineStyle.single.rawValuefor critical warnings - SF Symbols: Use
NSImage(systemSymbolName:accessibilityDescription:)for menu item icons - Emphasis: Use system colors like secondaryLabelColor and etc.
- Offset: Use offset for aligning text with other items and lines. Use the below constants.
- Bold:
- Do NOT use:
- Emoji: Never use emoji for menu item icons. Always use SF Symbols instead.
- RGB color: Use only pre-defined colors by system (systemGreen, systemOrange, and etc) to consider dark/light mode compatiblity.
- Exception:
- While you can't use color for text, progress bars and status indicators can use system color.
- You can use color for text which is right-aligned text only.
- Others
- Never use random spaces for separating label
- BEST:
- Left: "OpenRouter"
- Right: "$37.42" - Additional Custom View Label on the right with right-aligned text (by offset calculating)
- OK: "OpenRouter: $37.42"
- OK: "OpenRouter ($37.42)"
- NO: "OpenRouter $37.42" (stupid random spaces)
- BEST:
- USD
- Use only two decimals when expressing dollars. (e.g.
$00.00)
- Use only two decimals when expressing dollars. (e.g.
- Never use random spaces for separating label
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.
- yesterday First seen · 665 lines · 11,821 tokens per session scan A 0abf4dba012c
opencode-bar AGENTS.md is an instructions file published in the GitHub repository opgginc/opencode-bar (308 stars, last pushed 29d ago), licensed MIT. It adds 11,821 tokens to every session, about $0.0591 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.
Other instructions, from other repositories
imagine-mcp CLAUDE.md
Instructions for n24q02m/imagine-mcp, covering imagine-mcp, architecture, tool signatures, model selection and transport modes.
imagine-mcp AGENTS.md
Instructions for n24q02m/imagine-mcp, covering imagine-mcp, architecture, tool signatures, model selection and transport modes.
ui-ux-pro-max-skill CLAUDE.md
Instructions for nextlevelbuilder/ui-ux-pro-max-skill, covering claude.md, project overview, search command, architecture and sync rules.
gortex CLAUDE.md
Instructions for zzet/gortex, covering gortex, build & test, codebase overview, discovery (read once, then keep using) and llm provider (powers ask and searchsymbols assist: modes).
DevoxxGenieIDEAPlugin AGENTS.md
Instructions for devoxx/DevoxxGenieIDEAPlugin, covering agents.md, project overview, build & development commands, building and testing.
DevoxxGenieIDEAPlugin GEMINI.md
Instructions for devoxx/DevoxxGenieIDEAPlugin, a project described as: DevoxxGenie is an agentic plugin for IntelliJ IDEA that uses local LLM's (Ollama, LMStudio, GPT4All, Jan and Llama.cpp) and Cloud based LLMs to help review, test, explain your project code. Latest version now also supports Spec Driven Development…