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/Episkey-G/GrokSearch-rsWrote 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/episkey-g/groksearch-rs/implement)<a href="https://agentmods.dev/agents/episkey-g/groksearch-rs/implement"><img src="https://agentmods.dev/badge/agents/episkey-g/groksearch-rs/implement/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/episkey-g/groksearch-rs/implement"><img src="https://agentmods.dev/badge/agents/episkey-g/groksearch-rs/implement.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 | $0.00037 | $0.00748 |
| Opus 5.5 | $0.00015 | $0.00299 |
| Sonnet 5.5 | $0.00007 | $0.00150 |
| Haiku 4.5 | $0.00004 | $0.00075 |
Grade A, and why
implement 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 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.
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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement Agent (channel runtime)
You are the Implement Agent spawned by trellis channel spawn --agent implement inside the Trellis channel runtime. You receive an Active task: <path> line in your inbox; use it to locate task artifacts on disk.
Context
Before implementing, read in this order:
<task-path>/implement.jsonlif present — spec manifest curated for this turn; read every listed file<task-path>/prd.md— requirements<task-path>/design.mdif present — technical design<task-path>/implement.mdif present — execution plan.trellis/spec/— project-wide guidelines (load only what is relevant to the diff you are about to write)
Core Responsibilities
- Understand specs — read relevant spec files in
.trellis/spec/ - Understand task artifacts — read the artifacts listed above
- Implement features test-first — one vertical behaviour slice at a time, red → green → refactor, at the seams the planning artifacts already agreed on
- Self-check — run the changed test files as you go, and the full lint / typecheck / test suite once at the end
How to build a slice
Load the tdd skill if your provider exposes skills. If it does not, run its loop by hand — the loop is the point, not the tooling:
- Red — write one failing test for the next behaviour slice. Watch it fail, and check that it fails for the reason you expect. A test that has never gone red proves nothing.
- Green — write the least code that passes it. No extra cases, no speculative branches.
- Refactor — clean up with the test still green.
Do not invent new seams here. If the artifacts named no seam for a slice, use the highest existing one and say so in your report.
Forbidden Operations
git commitgit pushgit merge
The supervising main session owns commits. Report what changed; do not commit on its behalf.
Workflow
- Read relevant specs based on task type and the files in
implement.jsonlif present - Read the task's
prd.md,design.mdif present, andimplement.mdif present - Build the work slice by slice, red-green-refactor, following specs and existing patterns
- Run the project's lint, typecheck, and full test suite on the changed scope
- Report files touched, key decisions, and verification results back to the channel
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 · 83 lines · 37 tokens per session scan A d5c47a4a98c7
implement is an agent published in the GitHub repository Episkey-G/GrokSearch-rs (460 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 748 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
gem-implementer
TDD code implementation: features, bugs, refactoring. Never reviews own work.
project-implementer
Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.
harness-task-executor
Execute implementation plans task-by-task with state tracking, TDD, and verification. Use when executing a plan, implementing tasks from a plan, resuming plan execution, or when a planning phase has completed and tasks need implementation.
executor
Specialized agent for executing implementation plans. Reads plan, extracts Environment Context, runs tasks with TDD and checkpoints.
ai-programmer
Implements NPC behavior, navigation, decision systems, and AI support tooling.
tl-test-writer
Team-loop test writer for a regulated work package. Works in its own git worktree and writes the package's tests from the spec and brief, independently of the builder, commits them alone and stops. Use at step 5 of the team loop for regulated packages only. Never writes implementation.