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/car12o/claude-workflows/gopher-fixgit clone --depth 1 https://github.com/car12o/claude-workflowsWrote 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/car12o/claude-workflows/gopher-fix)<a href="https://agentmods.dev/commands/car12o/claude-workflows/gopher-fix"><img src="https://agentmods.dev/badge/commands/car12o/claude-workflows/gopher-fix.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 | $0.00024 | $0.01208 |
| Opus 5 | $0.00012 | $0.00604 |
| Sonnet 5 | $0.00005 | $0.00242 |
| Haiku 4.5 | $0.00002 | $0.00121 |
Grade A, and why
gopher-fix 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 3d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the gopher-fix orchestrator for Go 1.24+ projects.
Core rule: You are an orchestrator. Your job is to delegate work to specialized subagents via the Task tool, make decisions at stop points, and communicate with the user.
Bug Report
$ARGUMENTS
Workflow
Phase 1: Reproduce → go-implementer (write failing test)
Phase 2: Diagnose → go-analyzer (investigate root cause)
Phase 3: Fix → go-implementer (minimal code change)
→ go-quality-gate
→ git commit
Phase 4: Review → go-reviewer
No stop points — this workflow is autonomous for small, focused fixes. If the fix turns out to be complex (touching 5+ files or requiring interface changes), escalate to the user and suggest using /gopher-feat instead.
Subagent Reference
| Phase | Agent | subagent_type |
|---|---|---|
| Reproduce | go-implementer | gopher:go-implementer |
| Diagnose | go-analyzer | gopher:go-analyzer |
| Fix | go-implementer | gopher:go-implementer |
| Quality Gates | go-quality-gate | gopher:go-quality-gate |
| Review | go-reviewer | gopher:go-reviewer |
Phase 1: Reproduce
Use the Task tool with subagent_type: "gopher:go-implementer" to write a failing test that demonstrates the bug. Include in the task prompt:
- The bug description from $ARGUMENTS
- Instruction to write a test that fails due to the reported bug
- Instruction to use table-driven test format with a clear test name reflecting the bug
- Instruction to run the test and confirm it fails (RED phase only — do not fix it)
The implementer should return:
- The test file and test name
- The failure output proving the bug exists
- The package where the bug manifests
If the bug cannot be reproduced (test passes unexpectedly): report this to the user with the test that was written, and ask for clarification.
Capture the reproduction output for subsequent phases.
Phase 2: Diagnose
Use the Task tool with subagent_type: "gopher:go-analyzer" to investigate the root cause. Include in the task prompt:
- The bug description
- The failing test and its output from Phase 1
- The package where the bug manifests
- Instruction to trace the code path that leads to the failure
- Instruction to identify the root cause and the minimal set of files that need to change
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.
- 3d ago First seen · 125 lines · 24 tokens per session scan A 643d04ff9ddb
gopher-fix is a command published in the GitHub repository car12o/claude-workflows (2 stars, last pushed 6mo ago), licensed MIT. It adds 24 tokens to every session and 1,208 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 2026-08-31.
Other commands, from other repositories
cli-patterns
Reference patterns for implementing CLI commands in internal/cli/.
review
Review current changes for correctness, style, and potential issues.
OPSX: Fast Forward
Create a change and generate all artifacts needed for implementation in one go.
fix
Auto-fix linting, formatting, and common issues.
gum-auth-use-service-account
Configure the serviceaccountkey auth strategy.
gum-cache-stats
Command "gum-cache-stats" from ehmo/gum, covering gum cache stats, usage, parent, flags and see also.