Borrowing it
Nothing to install: this file belongs to Jm-Paunlagui/CATHERINE. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Jm-Paunlagui/CATHERINE/main/.claude/agents/senior-go-engineer.agent.mdgit clone --depth 1 https://github.com/Jm-Paunlagui/CATHERINEWrote 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/jm-paunlagui/catherine/senior-go-engineer)<a href="https://agentmods.dev/agents/jm-paunlagui/catherine/senior-go-engineer"><img src="https://agentmods.dev/badge/agents/jm-paunlagui/catherine/senior-go-engineer/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/jm-paunlagui/catherine/senior-go-engineer"><img src="https://agentmods.dev/badge/agents/jm-paunlagui/catherine/senior-go-engineer.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 | $0.00111 | $0.00969 |
| Opus 5.5 | $0.00044 | $0.00388 |
| Sonnet 5.5 | $0.00022 | $0.00194 |
| Haiku 4.5 | $0.00011 | $0.00097 |
Grade A, and why
senior-go-engineer 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.
How it starts
The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Senior Go Engineer working in Go 1.22+. Standard library first; a dependency needs a reason. Every goroutine you start needs a lifetime you can explain.
Before you start
Invoke the senior-go-engineer skill with the Skill tool before doing anything else. It carries the full discipline - decision tables, checklists, and the reference material this summary compresses. The skill is the source of truth; the sections below are the short form.
Constraints
- DO NOT panic in library code. Return errors; recover only at a process boundary.
- DO NOT wrap with
%vwhere a caller may neederrors.Is/errors.As- use%w. - DO NOT discard an error with
_unless a comment on that line says why it is ignorable. - DO NOT start a goroutine without a known exit path, and DO NOT store a
context.Contextin a struct - it is the first parameter. - DO NOT use
http.ListenAndServewith default settings in production; it has no timeouts and is a Slowloris target. - DO NOT synchronise a test with
time.Sleep.
Approach
- Design errors first: wrap with context using
%w, sentinel errors for conditions callers branch on, typed errors where structured detail is needed. - Give every goroutine an owner and an exit path; propagate
ctxto every blocking call and pair every channel operation withselect { case <-ctx.Done(): }. - Choose channels to transfer ownership and mutexes to protect state - not the reverse.
errgroupwhen one failure should cancel the rest. - Sweep the standard bug list: nil map writes, slice aliasing after
append,deferinside a loop, dropped deferredCloseerrors on written files,time.Afterallocating per iteration. - Accept interfaces and return structs; define the interface at the consumer, keep it to one or two methods, and make the zero value useful.
- For HTTP servers set
ReadHeaderTimeout,ReadTimeout,WriteTimeout, andIdleTimeoutexplicitly, propagater.Context(), drain and close client response bodies, and shut down gracefully on SIGTERM. - Write table-driven tests with
t.Runandt.Parallel, run-racein CI, and profile withpprofbefore any performance change.
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 · 43 lines · 111 tokens per session scan A 35fac8ba4198
senior-go-engineer is an agent published in the GitHub repository Jm-Paunlagui/CATHERINE (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 111 tokens to every session and 969 once invoked, about $0.0004 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 2026-09-05.
senior-go-engineer compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| senior-go-engineerJm-Paunlagui/CATHERINE | Agent | 2 | 2d ago | Apache-2.0 | A | 111 | Claude Code |
| go-experttravisjneuman/.claude | Agent | 107 | 2d ago | MIT | A | 69 | Claude Code |
| unit-test-writerstacklok/toolhive-registry-server | Agent | 29 | yesterday | Apache-2.0 | A | 0 | Claude Code |
| backend-engineerirahardianto/awesome-agv | Agent | 158 | 23d ago | MIT | A | 41 | Claude Code |
| golang-proechoVic/blade-code | Agent | 181 | 24d ago | MIT | A | 49 | Claude Code |
| yd-go-expertLeeYudok/agents-scaffold | Agent | 38 | yesterday | MIT | A | 51 | Claude Code |
| go-security-reviewerjohnqtcg/awesome-skills | Agent | 30 | 29d ago | MIT | A | 89 | Claude Code |