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 commands/sgaunet/claude-plugins/go-tddgit clone --depth 1 https://github.com/sgaunet/claude-pluginsWrote 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/commands/sgaunet/claude-plugins/go-tdd)<a href="https://agentmods.dev/commands/sgaunet/claude-plugins/go-tdd"><img src="https://agentmods.dev/badge/commands/sgaunet/claude-plugins/go-tdd.svg" alt="Measured on agentmods" 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 | $0.00021 | $0.01858 |
| Opus 5 | $0.00010 | $0.00929 |
| Sonnet 5 | $0.00004 | $0.00372 |
| Haiku 4.5 | $0.00002 | $0.00186 |
Grade A, and why
go-tdd 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 5d 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 — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Go TDD Implementation
Implement a Go feature using strict RED → GREEN → REFACTOR TDD methodology, with Context7 MCP integration for up-to-date library documentation at each phase.
Arguments
$argument: Feature description and optional flags (required)
Flags
| Flag | Short | Effect |
|---|---|---|
--skip-lint |
-l |
Skip golangci-lint in Phase 5 |
--skip-refactor |
-r |
Skip Phase 4 refactoring |
--dry-run |
-n |
Show plan only, no file writes |
--force |
-f |
Skip all user confirmations |
Error Handling
| Error | Action |
|---|---|
No go.mod found |
Abort with message: "Not a Go project — no go.mod found" |
| Context7 unavailable | Warn and continue without doc validation |
| Tests won't compile | Display errors, attempt fix (max 2 retries), then ask user |
| Tests fail in GREEN phase | Attempt fix (max 2 retries), then ask user |
| Lint failure | Attempt auto-fix, re-run, then ask user |
| Build failure | Display errors, abort |
Process
Phase 1: Discovery & Documentation (Automatic)
-
Parse flags from
$argument:- Extract feature description (everything before flags)
- Detect
--skip-lint/-l,--skip-refactor/-r,--dry-run/-n,--force/-f
-
Validate Go project:
- Check
go.modexists — if not, abort: "Not a Go project — no go.mod found" - Read
go.modto identify module name and Go version
- Check
-
Analyze project structure:
- Scan existing packages, test patterns, coding conventions
- Identify existing test helpers or shared fixtures
- Note the project's import style, error handling patterns, naming conventions
- Check existing
*_test.gofiles for package naming: flag any white box tests (package <pkgname>without_testsuffix) for potential conversion
-
Identify libraries needed for the feature:
- Determine which standard library packages are involved
- Determine which third-party libraries are needed
-
Fetch Context7 documentation for each library:
- Call
mcp__context7__resolve-library-idto get the library ID - Call
mcp__context7__query-docswith a query specific to the feature being implemented - If Context7 is unavailable, warn and continue without doc validation
- Call
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.
- 5d ago First seen · 207 lines · 21 tokens per session scan A d13cc76dddde
go-tdd is a command published in the GitHub repository sgaunet/claude-plugins (16 stars, last pushed 3d ago), licensed MIT. It adds 21 tokens to every session and 1,858 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.
Other commands, from other repositories
security-audit-static
Static security audit of AI-built code — map trust boundaries, cross-reference documented intent, self-refute every finding, and report only evidence-backed risks.
performance-audit-static
Static performance audit of AI-built code — find N+1 queries and request waterfalls, over-fetching, missing indexes, and caching opportunities, ranked by effort and impact.
document-app
Reverse-engineer an AI-built codebase into the system documents reviewers and auditors need — a core set (architecture, flows, permissions, variables) plus conditional docs (emails, cron, SEO, automation) when they apply.
plan-okrs
Brainstorm team-level OKRs aligned with company objectives — qualitative objectives with measurable key results.
write-stories
Break a feature into backlog items — user stories, job stories, or WWA format with acceptance criteria.
battlecard
Create a sales-ready competitive battlecard — positioning, feature comparison, objection handling, and win strategies.