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 skills add XnLemon/Neneko-skill --skill neneko-code-tastegit clone --depth 1 https://github.com/XnLemon/Neneko-skillWrote 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/skills/xnlemon/neneko-skill/neneko-code-taste)<a href="https://agentmods.dev/skills/xnlemon/neneko-skill/neneko-code-taste"><img src="https://agentmods.dev/badge/skills/xnlemon/neneko-skill/neneko-code-taste/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/skills/xnlemon/neneko-skill/neneko-code-taste"><img src="https://agentmods.dev/badge/skills/xnlemon/neneko-skill/neneko-code-taste.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 | $0.00051 | $0.00709 |
| Opus 5 | $0.00026 | $0.00354 |
| Sonnet 5 | $0.00010 | $0.00142 |
| Haiku 4.5 | $0.00005 | $0.00071 |
Grade A, and why
neneko-code-taste 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 10d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Neneko Code Taste
Apply this skill when the user wants new Go code or a review to feel native to tRPC-Agent-Go (or to a project deliberately adopting its engineering style). The goal is a small, clear, compatible change whose public API and lifecycle semantics are intentional. Treat the target repository's local conventions as the final authority when they conflict with an example below.
Working loop
Before editing:
- Identify the owning package and read its AGENTS.md, nearby constructors, options, interfaces, tests, and error paths. Search for an existing extension point before adding a new one.
- State the contract that must remain stable: defaults, nil behavior, errors, cancellation, ordering, resource lifetime, and exported API.
- Choose the smallest focused patch. Avoid unrelated refactors and avoid a new abstraction until its responsibility and ownership are clear.
While editing:
- Prefer concrete constructors; introduce an interface only when a consumer needs substitution or multiple implementations, and keep it consumer-owned.
- Keep implementation-specific types and configuration private to the owning package. Export only the narrow contract callers need.
- Put context.Context first in methods that accept it; propagate cancellation and do not store contexts in structs.
- Make goroutine, channel, timer, close, and shutdown ownership explicit. The creator owns cleanup unless the API documents a different contract.
- Return wrapped errors with lowercase, punctuation-free messages; use %w when callers need to inspect the cause. Do not silently discard meaningful errors.
- Match existing naming, option precedence, default initialization, copy/clone behavior, and Godoc/comment patterns.
After editing:
- Add or update tests that prove observable contracts (including defaults, invalid input, errors, cancellation, concurrency, and lifecycle where relevant), not merely line coverage or private implementation details.
- Run the narrowest relevant tests first, then repository formatting/import and lint checks. Use scripts/check.sh when it fits the target repository.
- Perform a second-pass API/design review of the final diff: exported surface, abstraction/ownership, compatibility, context propagation, concurrency, error semantics, and unrelated churn. Report residual risks explicitly.
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 70 lines · 51 tokens per session scan A 8a682a65b54e
neneko-code-taste is a skill published in the GitHub repository XnLemon/Neneko-skill (2 stars, last pushed 16d ago), licensed MIT. It adds 51 tokens to every session and 709 once invoked, about $0.0003 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 skills, from other repositories
go-code-reduce
Find and, when authorized, apply maintainable Go code reductions. Use when a user asks to reduce Go lines, boilerplate, duplication, or obsolete idioms without changing behavior; not for general implementation or style review.
mcore-linting-and-formatting
Linting and formatting for Megatron-LM. Covers running autoformat.sh, tools (ruff, black, isort, pylint, mypy), and code style rules.
golang-refactoring
Golang refactoring — safe, at-scale restructuring of existing Go code: a coverage-adaptive safety net, behavior-preserving transforms (gopls Rename/Extract, gofmt -r, gopatch), the Fowler catalog mapped to Go, breaking import cycles, and small stacked PRs. Apply when a function or type has grown too large, a code…
sapcc-review
Gold-standard SAP CC Go code review: 10 parallel domain specialists.
go-concurrency-safety
L1 supplement - audits Go-specific concurrency hazards in node client code: map iteration non-determinism, goroutine leaks, mutex ordering, panic boundaries, context cancellation.
design-review
Deep design review of Go codebase — naming, structure, consistency, interfaces, error handling. Scores each dimension and provides actionable fixes.