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.
git clone --depth 1 https://github.com/bdfinst/agentic-dev-teamWrote 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/agents/bdfinst/agentic-dev-team/go-quality)<a href="https://agentmods.dev/agents/bdfinst/agentic-dev-team/go-quality"><img src="https://agentmods.dev/badge/agents/bdfinst/agentic-dev-team/go-quality.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 5.1 | $0.00021 | $0.00443 |
| Opus 5 | $0.00010 | $0.00221 |
| Sonnet 5 | $0.00004 | $0.00089 |
| Haiku 4.5 | $0.00002 | $0.00044 |
Grade A, and why
go-quality 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.
What it actually says
Go Quality
Output JSON:
{"status": "pass|warn|fail|skip", "issues": [{"severity": "error|warning|suggestion", "confidence": "high|medium|none", "file": "", "line": 0, "message": "", "suggestedFix": ""}], "summary": ""}
Status: pass=idiomatic Go, warn=improvements needed, fail=error handling gaps Severity: error=ignored error or unsafe pattern, warning=non-idiomatic, suggestion=style Confidence: high=mechanical (handle error, remove naked return); medium=design choice; none=domain context
Context needs: diff-only
File scope: *.go
Activates when
go.mod exists.
Skip
Return skip when no .go files in the changeset.
Detect
Error handling:
- Ignored errors (
_ = someFunc()without justification) - Error not checked after function call that returns error
- Error wrapping without context (
return errinstead ofreturn fmt.Errorf("doing X: %w", err)) - Panics in library code (only acceptable in
mainor test helpers)
Returns:
- Naked returns in functions longer than a few lines
- Named return values that aren't needed for documentation or defer
Interfaces:
- Large interfaces (>5 methods) — prefer small, composable interfaces
- Interfaces defined by the implementer instead of the consumer
- Unused interface methods
Struct patterns:
- Embedding for code reuse rather than composition (prefer composition)
- Exported fields on structs that should be private
- Missing constructors for structs with required fields
Concurrency:
- Goroutine leaks (goroutine started without cancellation or done channel)
- Shared state without mutex or channel protection
sync.WaitGroupmisuse (Add after Go)
Ignore
Test files (test helpers may legitimately panic), generated code, vendor directory.
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 · 66 lines · 21 tokens per session scan A 6a86e67d3c9b
go-quality is an agent published in the GitHub repository bdfinst/agentic-dev-team (280 stars, last pushed 2d ago), licensed MIT. It adds 21 tokens to every session and 443 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 2026-09-05.
Other agents, from other repositories
Golang Code Review Agent
Evaluates code changes for correctness, style adherence, architecture alignment, testing coverage, and documentation completeness.
go-reviewer
Go code reviewer and QA. MUST BE USED to verify any Go change before it is declared done. Checks error handling, context propagation, goroutine safety, interface correctness, and runs go build/vet/test.
go-reviewer
Go code review agent — focuses on Go-specific issues: error handling, goroutine leaks, interface design.
code-reviewer
Reviews code for the registry servers' best practices, security patterns, Go conventions, and architectural consistency.
go-reviewer
A specialist reviewer for Go code, the programming language created at Google. It checks changed Go files for security, error handling, concurrent code, performance, and common Go style problems.
go-reviewer
Go-specific code reviewer. Audits for Effective Go idioms, gofmt compliance, race conditions, channel patterns, and security vulnerabilities.