Borrowing it
Nothing to install: this file belongs to shyamsridhar123/sharkbait. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/shyamsridhar123/sharkbait/main/.github/copilot-instructions.mdgit clone --depth 1 https://github.com/shyamsridhar123/sharkbaitWrote 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.
[](https://agentmods.dev/instructions/shyamsridhar123/sharkbait/copilot-instructions)<a href="https://agentmods.dev/instructions/shyamsridhar123/sharkbait/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/shyamsridhar123/sharkbait/copilot-instructions/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.
<a href="https://agentmods.dev/instructions/shyamsridhar123/sharkbait/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/shyamsridhar123/sharkbait/copilot-instructions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.02088 | $0.02088 |
| Opus 5 | $0.01044 | $0.01044 |
| Sonnet 5 | $0.00418 | $0.00418 |
| Haiku 4.5 | $0.00209 | $0.00209 |
Grade C, and why
sharkbait copilot-instructions.md scanned grade C with 1 finding 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 9d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
❌ **Destructive operations** without confirmation (rm -rf, DROP DATABASE) How it starts
The opening of the file, as written. The whole thing — 315 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sharkbait - GitHub Copilot Instructions
Project Overview
Sharkbait is an AI-powered coding assistant CLI tool built with:
- Runtime: Bun (TypeScript)
- LLM: Azure OpenAI GPT Codex 5.2
- Memory: Beads (bd CLI) for git-backed task tracking
- GitHub: git + gh CLI (no Octokit)
- UI: ink (React for terminals)
- CLI Framework: commander
Tech Stack Rules
NEVER deviate from the approved tech stack:
- ✅ Use Bun for runtime and TypeScript for all code
- ✅ Use Azure OpenAI API (never switch to other providers without approval)
- ✅ Use git + gh CLI for GitHub operations (never Octokit)
- ✅ Use ink for terminal UI components
- ✅ Use commander for CLI argument parsing
- ❌ Do NOT add new frameworks or major dependencies without discussion
Architecture
src/
├── cli.ts # Entry point with commander
├── agent/ # Agent loop and context management
├── llm/ # Azure OpenAI client
├── tools/ # Tool registry and implementations
├── ui/ # ink components
└── utils/ # Config, logging, errors
See docs/ARCHITECTURE.md and docs/TRD.md for detailed specifications.
Development Workflow
Before Making Changes
- Always read AGENTS.md - Contains mandatory project rules
- Check backlog: Run
backlog task listto see existing work - Search for related tasks: Use
backlog task search "query" - Link to a task: Start work with
backlog task start <id>
During Development
- Read before editing: Always use Read tool on files before modifying
- Make minimal changes: Change only what's necessary
- Follow existing patterns: Match the code style in surrounding files
- Test your changes: Run
bun testfor unit tests - Type check: Run
bun run typecheckbefore committing
Commit Requirements
All commits MUST include the task ID:
# ✅ Good
git commit -m "SB-001.02: Add input validation to login endpoint"
# ❌ Bad
git commit -m "Add validation"
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.
- 9d ago First seen · 315 lines · 2,088 tokens per session scan C e5fe7f9444fc
sharkbait copilot-instructions.md is an instructions file published in the GitHub repository shyamsridhar123/sharkbait (5 stars, last pushed 6mo ago), licensed MIT. It adds 2,088 tokens to every session, about $0.0104 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.