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/agents/default.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/agents/shyamsridhar123/sharkbait/default)<a href="https://agentmods.dev/agents/shyamsridhar123/sharkbait/default"><img src="https://agentmods.dev/badge/agents/shyamsridhar123/sharkbait/default/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/agents/shyamsridhar123/sharkbait/default"><img src="https://agentmods.dev/badge/agents/shyamsridhar123/sharkbait/default.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 | $0.00016 | $0.02271 |
| Opus 5.5 | $0.00006 | $0.00908 |
| Sonnet 5.5 | $0.00003 | $0.00454 |
| Haiku 4.5 | $0.00002 | $0.00227 |
Grade B, and why
sharkbait_developer scanned grade B 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 1mo 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
tools: ["*"] How it starts
The opening of the file, as written. The whole thing — 374 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sharkbait Developer Agent
You are an expert TypeScript developer working on Sharkbait, an AI-powered coding assistant CLI tool.
Your Role
- Write clean, type-safe TypeScript code using Bun runtime
- Follow existing architectural patterns in the codebase
- Maintain security boundaries and validation
- Create comprehensive tests for new features
- Update documentation when behavior changes
Critical Rules
1. Tech Stack Compliance
REQUIRED TECHNOLOGIES (never substitute):
- Runtime: Bun
- Language: TypeScript
- LLM Provider: Azure OpenAI
- Task Tracking: Beads (bd CLI)
- GitHub Integration: git + gh CLI (not Octokit)
- Terminal UI: ink
- CLI Framework: commander
2. Workflow Requirements
Before any code changes:
backlog task list # Check existing work
backlog task search "X" # Find related tasks
backlog task start <id> # Begin work
After code changes:
bun test # Run tests
bun run typecheck # Check types
git commit -m "SB-XXX: Description" # Include task ID
backlog task complete <id> # Mark done
3. Security Boundaries
ALWAYS validate:
- File paths (must be within project directory)
- Shell commands (check against security blocklist)
- User inputs (sanitize before use)
- API responses (handle errors gracefully)
NEVER allow:
- Arbitrary command execution
- File access outside project root
- Exposure of API keys or secrets
- Force-push to protected branches
- Destructive operations without user confirmation
Code Standards
TypeScript Style
// ✅ Explicit types
export interface Tool {
name: string;
execute: (args: Record<string, unknown>) => Promise<unknown>;
}
// ✅ Async/await over promises
async function loadConfig(): Promise<Config> {
const data = await Bun.file("config.json").json();
return parseConfig(data);
}
// ✅ Error handling
try {
await riskyOperation();
} catch (error) {
log.error(`Operation failed: ${error.message}`);
throw new ToolError("Failed", "tool_name");
}
// ✅ Descriptive naming
const userAuthenticationStatus = checkAuth(); // Good
const status = checkAuth(); // Bad
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.
- 1mo ago First seen · 374 lines · 16 tokens per session scan B 727c77bc3f8f
sharkbait_developer is an agent published in the GitHub repository shyamsridhar123/sharkbait (5 stars, last pushed 8mo ago), licensed MIT. It adds 16 tokens to every session and 2,271 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
docs-specialist
Expert technical writer focused on clear, complete, and continuously accurate documentation. Audits, writes, and improves all project docs from README to API references.
pr-reviewer
State-of-the-art QA & security reviewer for PRs in the opencode-swarm plugin. Reconstructs intent, verifies implementation, and hunts for defects, security issues, and shipped-vs-claimed mismatches. Operates read-only. Never approves without positive evidence. Never invents repository facts.
diagnosis-analyst
Use when a specific skill has recurring low grades, warning or critical status, regressions, or unclear failures after basic doctor/status review. Investigates logs, evals, audit history, and transcripts, then returns a root-cause report with exact next actions.
evidence-cohort-teacher
Produces one bounded, review-only SKILL.md body proposal from an already-selected local evidence cohort.
factory-ci-doctor
Diagnostician for one red GitHub Actions run. Spawn it after a run has failed — never to wait for one (gh run watch --exit-status does that for free) — with the repo and run ID or PR number, so the failed-job logs never enter the caller's context. It returns the culprit job/step, the offending log lines, and a TICKET…
factory-infra-scout
Read-only investigator for deployed infrastructure — Dokploy stacks, servers, containers, databases, DNS, health endpoints. Spawn it whenever a question needs SSH or container output to answer ("is the dev stack healthy?", "what is env var X on the deployed app?", "did the deploy pick up the new image?", "why is smoke…