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/gopherguides/gopher-ai/refactor-cleangit clone --depth 1 https://github.com/gopherguides/gopher-aiWhat 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 | $0.00014 | $0.01852 |
| Opus 5 | $0.00007 | $0.00926 |
| Sonnet 5 | $0.00003 | $0.00370 |
| Haiku 4.5 | $0.00001 | $0.00185 |
Grade A, and why
refactor-clean 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
If $ARGUMENTS is empty or not provided:
Find and clean dead code across the entire Go project.
Usage: /refactor-clean [path] [options]
Examples:
/refactor-clean- Analyze entire project for dead code/refactor-clean ./pkg/...- Analyze specific package tree/refactor-clean --dry-run- Report findings without applying fixes/refactor-clean ./internal/auth --dry-run- Report-only for a specific package
Analysis categories: unused exported functions/types, orphaned test files, overly complex functions, unused imports.
Workflow: detect tools → parallel-dispatch 4 analysis subagents → present findings report → apply fixes only after user confirmation → verify build + tests.
Set default: TARGET_PATH="./..." and proceed.
If $ARGUMENTS is provided:
Parse $ARGUMENTS:
- Argument starting with
./or a package pattern →TARGET_PATH --dry-run→ setDRY_RUN=true, defaultTARGET_PATH="./..."- Both: extract path to
TARGET_PATH, setDRY_RUN=true
Loop Initialization
!if [ ! -x "${CLAUDE_PLUGIN_ROOT}/scripts/setup-loop.sh" ]; then echo "ERROR: Plugin cache stale. Run /gopher-ai-refresh (or refresh-plugins.sh) and restart Claude Code."; exit 1; else "${CLAUDE_PLUGIN_ROOT}/scripts/setup-loop.sh" "refactor-clean" "COMPLETE"; fi
Step 1: Verify Go Project
if [ ! -f go.mod ]; then
echo "ERROR: No go.mod found. This command must be run from a Go project root."
exit 1
fi
head -5 go.mod
Capture the module path from go.mod for import analysis.
Step 2: Detect Available Analysis Tools
echo "=== Tool Detection ==="
which staticcheck 2>/dev/null && staticcheck --version || echo "staticcheck: NOT FOUND"
which deadcode 2>/dev/null || echo "deadcode: NOT FOUND (golang.org/x/tools/cmd/deadcode)"
which gocyclo 2>/dev/null || echo "gocyclo: NOT FOUND"
which gocognit 2>/dev/null || echo "gocognit: NOT FOUND"
which goimports 2>/dev/null || echo "goimports: NOT FOUND"
go version
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 · 164 lines · 14 tokens per session scan A ed9c0ff66548
refactor-clean is a command published in the GitHub repository gopherguides/gopher-ai (21 stars, last pushed 2d ago), licensed MIT. It adds 14 tokens to every session and 1,852 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
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.