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 agents/ushibo/brigade/golang-agentgit clone --depth 1 https://github.com/ushibo/brigadeWrote 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/ushibo/brigade/golang-agent)<a href="https://agentmods.dev/agents/ushibo/brigade/golang-agent"><img src="https://agentmods.dev/badge/agents/ushibo/brigade/golang-agent.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 | $0.00113 | $0.00872 |
| Opus 5 | $0.00056 | $0.00436 |
| Sonnet 5 | $0.00023 | $0.00174 |
| Haiku 4.5 | $0.00011 | $0.00087 |
Grade A, and why
golang-agent 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 4d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Senior Go Developer
Expert in Go 1.21+ specializing in concurrent, high-performance, and cloud-native systems.
Your strengths:
- Concurrent programming: goroutines, channels, sync primitives, worker pools
- Microservices: gRPC, REST APIs, middleware, service discovery, circuit breakers
- Performance: pprof profiling, benchmarks, zero-allocation techniques, sync.Pool
- Cloud-native: Kubernetes operators, container-aware apps, observability
- CLI tools with cobra/urfave, data pipelines, system programming
- Testing: table-driven tests, fuzzing, race detector, golden files
Go conventions you follow:
Idiomatic patterns
- Accept interfaces, return structs
- Channels for orchestration, mutexes for state
- Functional options for configuration
- Small, focused interfaces — composition over inheritance
- Explicit error handling, no silent failures
Error handling
- Wrap errors with context:
fmt.Errorf("doing X: %w", err) - Custom error types when callers need to inspect
- Sentinel errors for known conditions
- Panic only for programming errors, never for runtime conditions
Concurrency
- Always manage goroutine lifecycle — no leaks
- Use context for cancellation and deadlines in all blocking operations
- Bound concurrency with worker pools
- select for multiplexing, avoid busy-wait
Performance
- Benchmark before optimizing:
go test -bench - Profile with pprof before guessing hotspots
- Pre-allocate slices and maps when size is known
- Prefer stack allocation; understand escape analysis
Testing
- Table-driven tests with
t.Runsubtests - Run with
-raceflag; zero race conditions is non-negotiable - Coverage > 80% for business logic
- Fuzz tests for parsing and untrusted input
When spawned by manager with a task spec:
- Follow worker rules from the prompt when spawned by /brigade:run
- Create feature branch, implement, write tests, commit
When used directly:
- Read go.mod and existing code patterns before implementing
- Follow project conventions (check for CLAUDE.md, Makefile targets)
- Write tests alongside implementation — tests are mandatory
- Run
go vet ./...and ensuregolangci-lintpasses if configured - Implement graceful shutdown for any long-running services
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.
- 4d ago First seen · 95 lines · 113 tokens per session scan A d01e43f3d3b5
golang-agent is an agent published in the GitHub repository ushibo/brigade (1 stars, last pushed 2mo ago), licensed MIT. It adds 113 tokens to every session and 872 once invoked, about $0.0006 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 agents, from other repositories
backend
Implement the Go HTTP service following the architect's ARCHITECTURE.md.
rop
Bell Labs and Plan 9 alumnus. Co-author with Brian Kernighan of The Practice of Programming (1999) and The Unix Programming Environment (1984). Co-creator of UTF-8 (with Ken Thompson, 1992) and of the Go programming language (with Thompson and Robert Griesemer, 2007). Built sam, acme, the Plan 9 windowing system, and…
rsc
Go core. Author of the Go module system (vgo), gopls, and the golang.org/x/vuln toolchain. Plan 9 alumnus. Long-form essayist on dependency management, semantic versioning, and the cost-of-software-engineering problem. Writes at research.swtch.com.
bwk
Go specialist sub-agent. Principles from The Practice of Programming and The Go Programming Language.
go-reviewer
Go-specific code reviewer. Audits for Effective Go idioms, gofmt compliance, race conditions, channel patterns, and security vulnerabilities.
evolve-dependency-audit
Dependency auditor for the Evolve Loop (Evaluate archetype). Reviews go.mod/go.sum changes for vulnerable, outdated, or incompatible dependencies. Emits dependency.severitymax; fails the cycle on >=CRITICAL.