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/verifygit 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 | $0.00018 | $0.01544 |
| Opus 5 | $0.00009 | $0.00772 |
| Sonnet 5 | $0.00004 | $0.00309 |
| Haiku 4.5 | $0.00002 | $0.00154 |
Grade A, and why
verify 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
If $ARGUMENTS is empty or not provided:
Run verification on entire project.
Usage: /verify [path]. /verify (entire project), /verify ./pkg/..., /verify ./cmd/server/....
Workflow: go vet → go build → go test → golangci-lint (if available, with auto-fix) → check dev-server logs (Air/Vite) → fix issues automatically where safe, report others → loop until all blocking checks pass.
This is your pre-push sanity check.
Loop Initialization
!if [ ! -x "${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 "${CLAUDE_PLUGIN_ROOT}/scripts/setup-loop.sh" "verify" "COMPLETE"; fi
Configuration
TARGET_PATH="${ARGUMENTS:-./...}"
echo "Verifying: $TARGET_PATH"
Step 1: go vet (static analysis)
go vet $TARGET_PATH 2>&1
Format: file.go:line:col: message. Common: Printf format mismatches, unreachable code, shadowed variables.
If issues found, non-blocking: report with file:line refs, attempt obvious fixes (format strings, unreachable code), re-run vet to confirm. Continue regardless.
Step 2: go build (compilation) — BLOCKING
go build $TARGET_PATH 2>&1
If errors, auto-fix using build-fix patterns:
- Parse errors by file, group related errors
- Read failing files for context
- Identify root cause and apply minimal fixes:
- Missing imports → add or
go get - Unused imports → remove
- Type mismatches → fix conversions
- Missing deps →
go mod tidy - Undefined vars/funcs → check spelling, scope
- Missing imports → add or
- Re-run
go builduntil clean
Generated files — do NOT edit directly:
*_templ.go→ fix the source.templ, thentempl generate- sqlc output → fix the
.sql, thensqlc generate *_mock.go→ fix the interface, regenerate mocks
Cycle detection: track error signatures across iterations. If the same error reappears after a "fix," try an alternative approach. After 5 attempts on the same error, ask the user.
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 · 166 lines · 18 tokens per session scan A d69c27caef26
verify is a command published in the GitHub repository gopherguides/gopher-ai (21 stars, last pushed 3d ago), licensed MIT. It adds 18 tokens to every session and 1,544 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
go-review
Go code review for idiomatic patterns.
cli-patterns
Reference patterns for implementing CLI commands in internal/cli/.
generate-tests
Generate unit or integration tests for Go code following project patterns and coverage targets.
release-patch
验证 main 后发布下一个 patch，并验收 GoReleaser 产物.
review-golang
Run a comprehensive Go code review on git-changed files.
go-conventions
Scan the current Go repo and write .claude/go-conventions.md — a project-specific convention file that rules/go.md loads on every session instead of re-scanning the codebase from scratch. Use when starting work in a new Go repo, when conventions have drifted, or when --refresh is passed to merge in new patterns.