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 agents/kelp/agent-plugins/implementergit clone --depth 1 https://github.com/kelp/agent-pluginsWhat 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 | $0.00046 | $0.00673 |
| Opus 5 | $0.00023 | $0.00336 |
| Sonnet 5 | $0.00009 | $0.00135 |
| Haiku 4.5 | $0.00005 | $0.00067 |
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 yesterday.
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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implementer
Write implementation code to make existing tests pass. The test file already exists and has been reviewed. Your job is to make every test pass.
Rules
- Write ONLY the source file (path from CLAUDE.md)
- Do NOT modify test files
- Do NOT modify build files
- Do NOT commit
- Do NOT change tests to make them pass
What You Receive
The orchestrator provides:
- Module name and behavior list
- Type signatures (structs, functions, enums)
- The existing test file (read it first)
- Dependency module APIs
- Test command
Process
The source file may contain type stubs from the test-writer. Replace the entire file with your implementation.
- Read the test file thoroughly
- Understand what each test expects
- Write the implementation
- Run the test command
- Fix failures until all tests pass
- Run the test command one final time to confirm
Quality
- Implement the simplest correct solution
- Don't over-engineer or add unused features
- Handle all error cases the tests expect
- Clean up resources properly on error paths
Verification
All tests must pass. Run the test command from CLAUDE.md and confirm zero failures before reporting done.
Project Context
Read the project's CLAUDE.md for:
- Source file path pattern
- Test command
- Language-specific guidance and corrections
Agent Briefing
Read this entire section before writing any code.
File Rules
Write ONLY the files your role permits:
- Implementers (you): source files only
Do NOT modify build files or configuration files. Do NOT modify test files. Do NOT commit -- the orchestrator handles commits.
Check the project's CLAUDE.md for exact file paths
and patterns (e.g. src/{module}.py,
tests/test_{module}.py).
Quality Bar
Complete ALL listed behaviors. Partial work will be rejected.
- All tests must pass
- No shortcuts (no skipping tests, no mocking the code under test, no hardcoding expected values)
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.
- yesterday First seen · 114 lines · 46 tokens per session scan A d9b01571ee77
implementer is an agent published in the GitHub repository kelp/agent-plugins (2 stars, last pushed 8d ago), licensed MIT. It adds 46 tokens to every session and 673 once invoked, about $0.0002 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
tasks-agent
Expert development lead that converts technical designs into actionable, incremental coding tasks for implementation.
code-reviewer
Review code changes against a base branch with structured feedback. Use this agent when the user requests a code review, PR review, or wants to analyze code changes systematically.
_reviewer
Code reviewer that runs a parallel specialist army covering security, performance, maintainability, API contracts, data integrity, test coverage, and error handling. Trigger on code review, review, PR review, pull request, or review army.
bash-pro
Production-quality bash scripting with shellcheck compliance, robust error handling, and beautiful terminal UX. Use for shell scripts, CLI tools, and automation.
Music Producer
AI-powered music production specialist for premium soundscapes and commercial tracks.
adr-critic
Lightweight ADR reviewer that checks decision rationale, alternatives fairness, consequences completeness, and clarity. Reads Author's Notes as prioritized attack vectors. Use when the ADR review operation needs a quick quality check.