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 EliasOulkadi/shokunin --skill senior-engineergit clone --depth 1 https://github.com/EliasOulkadi/shokuninWrote 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/eliasoulkadi/shokunin/senior-engineer)<a href="https://agentmods.dev/skills/eliasoulkadi/shokunin/senior-engineer"><img src="https://agentmods.dev/badge/skills/eliasoulkadi/shokunin/senior-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/skills/eliasoulkadi/shokunin/senior-engineer"><img src="https://agentmods.dev/badge/skills/eliasoulkadi/shokunin/senior-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00088 | $0.03934 |
| Opus 5 | $0.00044 | $0.01967 |
| Sonnet 5 | $0.00018 | $0.00787 |
| Haiku 4.5 | $0.00009 | $0.00393 |
Grade A, and why
Senior Engineer Coding 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 12d 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 — 440 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Senior Engineer Coding
Mindset
Write code for the next engineer who has to change it at 2am with no context. Clean code is risk management. Every production incident traces back to unclear, poorly structured, or hard-to-change code — not missing cleverness.
The standard: a teammate can safely change the code without fear, and explain what it does after a quick read.
1. Naming — Highest ROI Habit
Good names eliminate comments, prevent misunderstandings, and make refactoring safe.
Rules:
- Name by intent, not by type or storage:
emailAddressnotemailString - Use domain language: reflect business concepts (
Invoice,Subscription,Refund) - Include units in names:
timeoutMs,priceCents,fileSizeBytes - Make booleans read as questions:
isEnabled,hasAccess,shouldRetry - Name from the caller's perspective:
order.chargePayment()notorder.process() - Be consistent: one concept, one word. Never
userin one place andcustomerin another for the same entity
Avoid:
- Noise words:
manager,helper,data,info,handler(unless genuinely descriptive) - Abbreviations that don't scale:
usrAcctMgr,calcDisc - Overly generic verbs:
process(),handle(),doWork(),run() - Single-letter variables outside tiny loops:
d,x,tmpcause real production bugs
2. Functions — Small, Focused, Predictable
One function = one job. If you can't describe it in one sentence, it does too much.
Guard clauses over nested ifs:
// Wrong — pyramid of doom, hides assumptions
if (user != null) {
if (user.isActive()) {
if (hasAccess(user)) {
process(user)
}
}
}
// Right — early returns, happy path stays flat
if (user == null) return
if (!user.isActive()) return
if (!hasAccess(user)) return
process(user)
Limit parameters:
- More than 3 parameters → create a request/options object
- Long param lists break silently when order is swapped; objects don't
Separate computation from I/O:
- Pure logic (calculation, transformation) → separate from functions that read files, call APIs, write DBs
- Pure functions are easier to test, easier to reason about, and have no hidden side effects
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.
- 12d ago First seen · 440 lines · 88 tokens per session scan A 170c67998f96
Senior Engineer Coding is a skill published in the GitHub repository EliasOulkadi/shokunin (113 stars, last pushed 1mo ago), licensed MIT. It adds 88 tokens to every session and 3,934 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
python-docs
Create, update, and sync Python project documentation from source code. Use when asked to document a module, generate API references, create architecture diagrams with Mermaid, update docs after code changes, or keep documentation in sync with source. Triggers include "document", "write docs", "update docs", "sync…
code-refactor
Refactor Python code to match this repo's coding standards and style. Use when the user asks to "refactor", "clean up", "fix coding standards", or "apply best practices" to a module, file, or directory in this repo. Applies python-best-practices, pydantic v2, pytorch-lightning, and python-docs conventions as relevant…
quality
PALADIN quality gatekeeper. Two-stage system: Stage 1 checks spec compliance (pass/fail, blocks everything on failure). Stage 2 scores project health 0-100 across 6 tiers. Issues verdict: SHIP IT / SHIP WITH CAUTION / NOT READY / BLOCKED. Evidence Before Claims: every finding must cite the file, line, and what was…
refresh
Use when an existing contextualizer's references may have drifted from current upstream state — typically weekly, or whenever a few days of upstream changes have accumulated — to bring them back into agreement.
distill-habits
Review recent Claude Code conversations, distill the user's stable habits and preferences, persist them into a long-term habit ledger, and maintain a "My Habits" block in the global CLAUDE.md within a character budget. The more you use Claude Code, the more it knows you. Trigger manually with /distill-habits, or on a…
apply
Use when a staged proposal has been reviewed and signed off — REVIEW.md Step 3 ticked reviewed or provisional — and is ready to promote into the live contextualizer.