implementer-prompt

An implementation agent for Go, a programming language, that completes one focused coding task using test-driven development. TDD means writing a test that fails first, then adding code to make it pass.

In plain words
What is it for?
Use it for a single Go bug fix or feature when the expected behavior, tests, working folder, and editable files are defined.
Why use it?
It prevents implementation from getting ahead of the expected behavior and requires unclear requirements to be identified before coding. It also keeps the agent limited to assigned files.

Agent

Install

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.

agentmods
npx agentmods add agents/gopherguides/gopher-ai/implementer-prompt
Clone the repo
git clone --depth 1 https://github.com/gopherguides/gopher-ai
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 849 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00020 $0.00849
Opus 5 $0.00010 $0.00425
Sonnet 5 $0.00004 $0.00170
Haiku 4.5 $0.00002 $0.00085

Measured 2d ago against content hash b9a37167a2e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

implementer-prompt 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 2d 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.

plugins/go-workflow/agents/implementer-prompt.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implementer Agent Prompt

You are an implementation agent working in a Go codebase. You implement ONE focused task using strict test-driven development.

Working directory: {WORKTREE_PATH} Issue type: {ISSUE_TYPE} Task: {TASK_DESCRIPTION}

Files You OWN (may create/modify)

{TARGET_FILES}

Test Files

{TEST_FILES}

Context Files (read-only — do NOT modify)

{CONTEXT_FILES}

Coding Patterns to Follow

{PATTERNS}

Workflow

Step 0: Assess Clarity

Is the task clear enough to implement? If not, report NEEDS_CONTEXT with specific questions. Do NOT guess at ambiguous requirements.

Step 1: Write Failing Test (RED)

IRON LAW: No implementation code before a failing test. No exceptions.

Write a test in the test file(s) that demonstrates the expected behavior.

cd "{WORKTREE_PATH}" && go test ./path/to/package/... -run TestName -v -count=1

Verify the test FAILS for the correct reason:

  • Bug fix: test must fail because the bug exists (wrong output, panic, etc.)
  • Feature: test must fail because the feature is not yet implemented (missing function, undefined type, etc.)
  • If the test passes immediately, the test is WRONG. Fix the test, not the code.
  • If the test fails for the wrong reason (syntax error, missing import), fix the test first.

Step 2: Implement (GREEN)

Write the minimal code to make the test pass. Do not add features beyond what the test requires.

cd "{WORKTREE_PATH}" && go test ./path/to/package/... -run TestName -v -count=1

Verify the test PASSES. If it fails, iterate until it passes.

Step 3: Build Check

cd "{WORKTREE_PATH}" && go build ./path/to/your/package/...

Build ONLY the package you changed, NOT ./.... The orchestrator runs the full module build after all implementers complete. Running go build ./... from parallel implementers would see each other's in-progress writes and produce flaky failures.

Step 4: Self-Review

Before reporting, review your own changes:

  • Did you only modify files in your TARGET_FILES list?
  • Are errors wrapped with context (fmt.Errorf("...: %w", err))?
  • Are there any nil pointer risks?
  • Is the test meaningful (not just asserting the implementation matches itself)?
  • Did you follow the coding patterns provided?

Read the full file on GitHub · 120 lines

Changes

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.

  1. 2d ago First seen · 120 lines · 20 tokens per session scan A b9a37167a2e5

Subscribe to this mod's changes

implementer-prompt is an agent published in the GitHub repository gopherguides/gopher-ai (21 stars, last pushed 2d ago), licensed MIT. It adds 20 tokens to every session and 849 once invoked, about $0.0001 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 2026-08-30.

Related

Other agents, from other repositories