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/chmouel/jayrah/web-uigit clone --depth 1 https://github.com/chmouel/jayrahWhat 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 | $0.00498 | $0.00498 |
| Opus 5 | $0.00249 | $0.00249 |
| Sonnet 5 | $0.00100 | $0.00100 |
| Haiku 4.5 | $0.00050 | $0.00050 |
Grade A, and why
jayrah web-ui.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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web UI Development Instructions
Development Workflow
The Jayrah web UI is built with FastAPI backend and vanilla HTML/CSS/JavaScript frontend.
Running the Web Server
Use the Makefile command for development:
make web
This starts the web server with:
- Auto-reload enabled: Changes to files automatically restart the server
- Reload directory: Watches
./jayrah/ui/webfor changes - Hot reload: No need to manually kill/restart the server during development
File Structure
jayrah/ui/web/server.py- FastAPI backend serverjayrah/ui/web/index.html- Frontend HTML/CSS/JavaScript (single page app)
Key Features Implemented
- Full screen layout: Uses entire viewport with responsive design
- Horizontal scrolling: Issue list table scrolls horizontally by default
- Custom fields support: Displays Jira custom fields same as TUI
- Markdown rendering: Converts Jira markup to HTML using marked.js
- Real-time search: Debounced search with backend filtering
- Professional UI: Inbox-style layout matching TUI workflow
Development Notes
- No manual restarts needed: Thanks to
--reload, just save files and refresh browser - Shared logic: Common functions moved to
jayrah/ui/shared_helpers.pyto avoid circular imports - Config compatibility: Uses same
~/.config/jayrah/config.yamlas TUI - API endpoints:
/api/issues- List issues with optional search/api/issue/{key}- Get issue details with custom fields config/api/config- Get configuration including custom fields
- Always use make web which does auto reload and hot reload
Testing Changes
- Make changes to
server.pyorindex.html - Save the file (uvicorn will auto-reload)
- Refresh browser at http://127.0.0.1:8000
- No need to kill/restart the server process
External Dependencies
- marked.js: Loaded from CDN for Jira markdown → HTML conversion
- FastAPI: Backend framework
- Uvicorn: ASGI server with hot reload capability
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.
- 2d ago First seen · 60 lines · 498 tokens per session scan A ea3141119990
jayrah web-ui.instructions.md is an instructions file published in the GitHub repository chmouel/jayrah (3 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 498 tokens to every session, about $0.0025 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.
Other instructions, from other repositories
Browser4 CLAUDE.md
Instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.
agentic-playwright selectors.instructions.md
Instructions for idavidov13/agentic-playwright, covering selector strategy, critical, instructions, phase 1: open and authenticate and phase 2: explore like a user.
scrapai-cli CLAUDE.md
Instructions for discourselab/scrapai-cli, covering claude.md, 1. who you are, 2. hard rules, 3. tools and 4. before you start: confirm the project.
chromeboost CLAUDE.md
Instructions for lordamdal/chromeboost, covering chromeboost — repo-developer guide, what chromeboost is, repository layout, development commands and tests/antibot/ (run locally; not in ci).
skills CLAUDE.md
Instructions for aemcoder/skills, covering claude.md, repository structure, slicc browser automation conventions, stateless tab targeting (since slicc pr #188) and tab-new returns a targetid.
ultra-jira-mcp CLAUDE.md
Instructions for criblio/ultra-jira-mcp, covering ultra-jira-mcp — agent guide, layout, mental model, two modes — pick the right one and what lives where (toolkit vs. this repo).