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/d-padmanabhan/agent-engineering-handbookWrote 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/d-padmanabhan/agent-engineering-handbook/go)<a href="https://agentmods.dev/commands/d-padmanabhan/agent-engineering-handbook/go"><img src="https://agentmods.dev/badge/commands/d-padmanabhan/agent-engineering-handbook/go/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/commands/d-padmanabhan/agent-engineering-handbook/go"><img src="https://agentmods.dev/badge/commands/d-padmanabhan/agent-engineering-handbook/go.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 | $0.00013 | $0.00398 |
| Opus 5.5 | $0.00005 | $0.00159 |
| Sonnet 5.5 | $0.00003 | $0.00080 |
| Haiku 4.5 | $0.00001 | $0.00040 |
Grade A, and why
go 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 2mo 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 MODE ACTIVATED
You are now in GO MODE. Any work on Go code MUST follow:
rules/210-go.mdc(idiomatic, secure Go)rules/100-core.mdc(minimal, production-ready changes)rules/310-security.mdc(no secrets, OWASP-minded)
Use this command when the user asks to:
- Create new Go packages/types/functions
- Modify existing Go code
- Review Go code for correctness/security/performance
Guardrails (mandatory)
- Handle all errors explicitly.
- Keep interfaces small; prefer dependency injection where it improves testability.
- Avoid logging secrets; redact tokens/headers.
- Minimal diffs; no unrelated refactors.
Step 0: Determine intent (create vs modify vs review)
Infer intent from the user’s request. If ambiguous, ask ≤3 clarifying questions (Go version, package boundaries, API expectations).
Create
Produce complete, buildable code with:
- Clear package structure
- Context-aware APIs where appropriate (
context.Context) - Meaningful errors (
fmt.Errorf("...: %w", err))
Modify
- Preserve behavior unless requested otherwise
- Prefer minimal diffs
- Update tests only if needed/asked
Review
Prioritize:
- Critical: error handling omissions, unsafe concurrency, insecure network defaults, injection/SSRF patterns
- Recommended: allocations/perf hot spots, poor cancellation/timeouts, observability gaps
- Optional: style and minor simplifications
Verification (as applicable):
gofmt -w .
go test ./...
pre-commit run --all-files
Done condition
End with:
- Files changed (or “no changes made”)
- How to validate (build/test/lint) and expected behavior
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.
- 2mo ago First seen · 66 lines · 13 tokens per session scan A 69e2d2e60acb
go is a command published in the GitHub repository d-padmanabhan/agent-engineering-handbook (20 stars, last pushed yesterday), licensed MIT. It adds 13 tokens to every session and 398 once invoked, about $0.0001 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.
go compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| god-padmanabhan/agent-engineering-handbook | Command | 20 | yesterday | MIT | A | 13 | Claude Code |
| check-goarmanzeroeight/fastagent-plugins | Command | 29 | 3mo ago | MIT | A | 16 | Claude Code |
| skill-go-gin-apidewtech-technologies/dare-method | Command | 5 | 3mo ago | MIT | A | 0 | Claude Code |
| go-testcodelably/harmony-claude-code | Command | 43 | 8mo ago | MIT | A | 50 | Claude Code |
| go-reviewloulanyue/awesome-claude-notes | Command | 271 | 1mo ago | MIT | A | 7 | Claude Code, OpenCode |
| trex.verifyopenshift-online/agent-control-plane | Command | 13 | 5d ago | MIT | A | 0 | Claude Code |
| gopher-fixcar12o/claude-workflows | Command | 2 | 8mo ago | MIT | A | 24 | Claude Code |