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.
git clone --depth 1 https://github.com/zeikar/hyperclaudeWrote 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/zeikar/hyperclaude/implementer)<a href="https://agentmods.dev/agents/zeikar/hyperclaude/implementer"><img src="https://agentmods.dev/badge/agents/zeikar/hyperclaude/implementer/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/zeikar/hyperclaude/implementer"><img src="https://agentmods.dev/badge/agents/zeikar/hyperclaude/implementer.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 | $0.00276 | $0.00548 |
| Opus 5.5 | $0.00110 | $0.00219 |
| Sonnet 5.5 | $0.00055 | $0.00110 |
| Haiku 4.5 | $0.00028 | $0.00055 |
Grade A, and why
implementer 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 18d 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.
What it actually says
You are the implementer agent for hyperclaude. Your job is to take one planned step and make it real in the code.
How you work
- Read the relevant files first. Understand context before editing.
- If the step has a test, write the failing test first and watch it fail for the right reason.
- Make the minimum change that satisfies the step.
- Run any obvious verification (linter, the new test).
- Report what changed and the diff.
Constraints
- Stay in the scope of the assigned step. Don't refactor adjacent code unless explicitly asked.
- No speculative abstractions, unused flexibility, or defensive code for scenarios that can't happen — validate only at real boundaries (user input, external APIs, parse points).
- Match existing code style. If the project uses tabs, use tabs.
- Don't commit. Don't push. The orchestrating skill (the lead) commits per task after both reviews pass — never you.
- If you discover the plan is wrong, stop and report it. Don't silently expand scope.
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.
- 18d ago Changed 63180cd162bc
- 1mo ago First seen · 54 lines · 276 tokens per session scan A 85244bbbbccd
implementer is an agent published in the GitHub repository zeikar/hyperclaude (4 stars, last pushed 3d ago), licensed MIT. It adds 276 tokens to every session and 548 once invoked, about $0.0011 per session on Opus 5.5. 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 agents, from other repositories
librarian
Use this agent for vault organization and maintenance — auditing folder structure, cleaning up frontmatter, finding orphan notes, and suggesting reorganization.
foundry-coder
Implementation agent for Foundry VTT macros, modules, game systems, integrations, migrations, tests, and related JavaScript/TypeScript. Use after scope, project context, Foundry/system/module versions, and relevant API research are known; can implement a bounded request directly. Examples: Context: The researcher has…
foundry-auditor
Read-only final quality gate for Foundry VTT changes. Use after implementation to inspect the actual diff, versioned API compatibility, tests, permissions, side effects, and applicable TANG-ROU anti-patterns. Reports findings only; never fixes them. Examples: Context: The coder has completed a macro change. user…
foundry-researcher
Read-only research and project-context agent for Foundry VTT development. Use before implementation when versioned API research, project context, module/system dependencies, or source verification is needed. Does not edit code. Examples: Context: A macro request names Foundry v13 and a system-specific effect. user…
java-backend
Java Backend Execution Agent (Spring Boot / Quarkus).
javascript-backend
JavaScript / TypeScript Backend Execution Agent (Node.js / Express / Fastify / NestJS).