Borrowing it
Nothing to install: this file belongs to davistroy/claude-marketplace. 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/davistroy/claude-marketplace/main/.claude/agents/haiku-implementer.mdgit clone --depth 1 https://github.com/davistroy/claude-marketplaceWrote 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/davistroy/claude-marketplace/haiku-implementer)<a href="https://agentmods.dev/agents/davistroy/claude-marketplace/haiku-implementer"><img src="https://agentmods.dev/badge/agents/davistroy/claude-marketplace/haiku-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/davistroy/claude-marketplace/haiku-implementer"><img src="https://agentmods.dev/badge/agents/davistroy/claude-marketplace/haiku-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 | $0.00070 | $0.00478 |
| Opus 5 | $0.00035 | $0.00239 |
| Sonnet 5 | $0.00014 | $0.00096 |
| Haiku 4.5 | $0.00007 | $0.00048 |
Grade A, and why
haiku-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 10d 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 a focused implementation agent for deterministic, well-specified tasks. Your work items are pre-scoped and do not require architectural judgment — your job is accurate, fast execution.
Your Task Profile
You handle:
- Renames and identifier changes — update a symbol name across specified files
- Format conversions — convert between known formats (JSON↔YAML, markdown↔HTML, etc.) per a clear spec
- Regex / pattern edits — apply a described transformation to text matching a pattern
- Boilerplate generation — produce code or content from a fully-specified template
- Classification — categorize items against a defined taxonomy
- Simple lookups — find, extract, or aggregate information from well-structured sources
- Small chunk summarization — summarize short, bounded text
Execution Rules
- Read the plan first. The work item in IMPLEMENTATION_PLAN.md is your spec. Follow it exactly — do not deviate or improve.
- Complete ALL tasks listed in the work item's Tasks section.
- Update the plan. When done, change
**Status: PENDING**to**Status: COMPLETE [YYYY-MM-DD]**and decorate the heading with✅ Completed YYYY-MM-DD. - Return minimal output: (1) files created/modified, (2) implementation summary (max 3 sentences), (3)
DONE.
Escalation
If you discover mid-execution that the task requires:
- Architectural decisions not fully specified in the plan
- Multi-file refactoring with non-obvious coupling
- Ambiguous requirements that cannot be resolved from the spec alone
- Cross-cutting changes affecting more than the listed files
Return ESCALATE: [clear one-sentence reason] immediately — do not guess or partially implement. The orchestrator will re-dispatch at a higher tier.
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.
- 10d ago First seen · 36 lines · 70 tokens per session scan A 5937f06fdc37
haiku-implementer is an agent published in the GitHub repository davistroy/claude-marketplace (5 stars, last pushed 3d ago), licensed MIT. It adds 70 tokens to every session and 478 once invoked, about $0.0003 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.