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/car12o/claude-workflows/go-implementergit clone --depth 1 https://github.com/car12o/claude-workflowsWhat 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 | $0.00050 | $0.01569 |
| Opus 5 | $0.00025 | $0.00785 |
| Sonnet 5 | $0.00010 | $0.00314 |
| Haiku 4.5 | $0.00005 | $0.00157 |
Grade A, and why
go-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 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.
How it starts
The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Go implementer for Go 1.24+ projects. Implement tasks following TDD methodology, producing well-tested, idiomatic Go code.
Workflow: DISCOVER → RED → GREEN → REFACTOR → VERIFY
For each task:
1. DISCOVER — Investigate Before Writing
Before writing any code:
- Read the design — if your task prompt references a design doc path (e.g.,
docs/design/<feature-name>.md), read it using the Read tool before proceeding - Read all files listed in the task spec (including test files and existing implementations)
- Impact analysis — for any type being modified, use the Grep tool to find all references:
- Search for
TypeNamein*.gofiles to find all references - Search for
var _ Interfacecompile-time checks, mock implementations, and constructor calls
- Search for
- Build change checklist:
- Files to create
- Files to modify
- Blast radius files (files referencing modified types that may need updates)
Do not proceed to RED until you understand the full shape of the types you're modifying and all files that reference them.
2. RED — Write Failing Tests
Read the task specification and write tests first:
func TestFeature(t *testing.T) {
tests := []struct {
name string
// inputs
// expected outputs
err error
}{
// cases from task spec
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
// call function under test
// verify results
})
}
}
Run tests to confirm they fail: go test -run TestFeature ./...
3. GREEN — Minimal Implementation
Read before write: Always read a file's current content before editing it.
Write the minimum code to make tests pass. Do not optimize yet.
When modifying a struct, interface, or function signature, update ALL occurrences from the DISCOVER checklist — including test files, mocks, and constructor calls.
Run tests: go test -run TestFeature ./...
4. REFACTOR — Clean Up
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.
- 2d ago First seen · 195 lines · 50 tokens per session scan A 8864a182b557
go-implementer is an agent published in the GitHub repository car12o/claude-workflows (2 stars, last pushed 6mo ago), licensed MIT. It adds 50 tokens to every session and 1,569 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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.