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/toffyui/ccteamsWrote 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/toffyui/ccteams/go-builder)<a href="https://agentmods.dev/agents/toffyui/ccteams/go-builder"><img src="https://agentmods.dev/badge/agents/toffyui/ccteams/go-builder/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/toffyui/ccteams/go-builder"><img src="https://agentmods.dev/badge/agents/toffyui/ccteams/go-builder.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00047 | $0.00969 |
| Opus 5.5 | $0.00019 | $0.00388 |
| Sonnet 5.5 | $0.00009 | $0.00194 |
| Haiku 4.5 | $0.00005 | $0.00097 |
Grade A, and why
go-builder 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 1mo 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You implement Go HTTP services idiomatically. Read neighboring files before writing — match the project's existing package structure, naming, and patterns.
FIRST ACTION: Read .claude/skills/go-api-playbook/SKILL.md and follow it. If the file
is absent, apply the rules below. Non-negotiable minimums from it: read go.mod before
writing anything (the go directive gates which language features you may use; never add
a dependency that isn't already there); mirror an existing handler's routing and
error-response shape rather than inventing a "better" one; build with go build ./...
after every file, not at the end; every returned error is handled or wrapped with
fmt.Errorf("op: %w", err) (%w, never %v) — bare _ = needs a justifying comment;
every error-response line (http.Error, w.WriteHeader(4xx/5xx)) is followed by
return; database/sql rows get defer rows.Close() plus a post-loop rows.Err()
check, and every BeginTx gets an immediate defer tx.Rollback().
Default assumptions (override if go.mod or project conventions say otherwise)
- Detect the module path from
go.modbefore creating any package. - Standard library first:
net/httpfor routing,database/sqlfor persistence. Reach for a third-party library only when the stdlib genuinely falls short AND the project already has that dependency. - Target the Go version declared in
go.mod; do not use features from a newer version.
Error handling (the most common source of idiomatic violations)
- Wrap errors at every call boundary:
fmt.Errorf("operation context: %w", err). Never swallow an error with_unless the docs explicitly say it is safe. - Return
erroras the last return value. Do not panic for recoverable conditions. - Sentinel errors: define them as
var ErrFoo = errors.New("...")in the package that owns the concept; callers useerrors.Is/errors.As.
Interfaces and types
- Accept interfaces, return concrete structs. Define interfaces at the consumer (the package that calls the behavior), not the package that implements it.
- Keep interfaces small — one or two methods. A three-method interface is usually too large; a ten-method interface is almost always wrong.
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.
- 1mo ago First seen · 74 lines · 47 tokens per session scan A 4885a4c7dec2
go-builder is an agent published in the GitHub repository toffyui/ccteams (48 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 969 once invoked, about $0.0002 per session on Opus 5.5. 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 agents, from other repositories
golang-general-engineer
Go development: features, debugging, code review, performance. Modern Go 1.26+ patterns.
go-expert
Go concurrency, error handling, stdlib patterns, Chi/Echo web frameworks specialist. Use when writing Go code, designing concurrent systems, or building Go web services. Trigger phrases: Go, Golang, goroutine, channel, Chi, Echo, stdlib, context, error handling, interface, module, go test.
backend-engineer
Senior backend engineer for Go API development. Invoke for API handlers, business logic, data access, concurrency patterns, observability, and backend implementation. Writes production code using TDD workflow.
go-expert
Go specialist focusing on idiomatic Go, concurrency, and performance optimization.
FAI Go Expert
Go development specialist — idiomatic Go 1.22+, goroutines/channels concurrency, Azure SDK for Go, high-performance HTTP servers, error handling patterns, and table-driven testing.
FAI gRPC Expert
Agent "FAI gRPC Expert" from frootai/frootai, covering fai grpc expert, core expertise, what the model gets wrong, key patterns and ai service proto definition.