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 agentmods add skills/oleg494/coding-kit/architecture-simplicitynpx skills add oleg494/coding-kit --skill architecture-simplicitygit clone --depth 1 https://github.com/oleg494/coding-kitWhat 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 | $0.00119 | $0.01013 |
| Opus 5 | $0.00060 | $0.00507 |
| Sonnet 5 | $0.00024 | $0.00203 |
| Haiku 4.5 | $0.00012 | $0.00101 |
Grade A, and why
architecture-simplicity 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 2d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture & simplicity: design principles
1. Simplicity and dependency
- YAGNI UNTIL SECOND NEED — an abstraction with one consumer is debt, not architecture. Inline until a second consumer; only then extract. A layer you can remove means the same behavior with less code.
- STD LIB / PLATFORM BEFORE DEPENDENCY — a new dependency costs more than 30 lines of your own code (often). Start with stdlib/native; add a dep only if the pain is measurable. moment.js for a single format = no.
- SEPARATE MODULES BY CHANGE REASON — generators.py, payments.py, access.py, bot.py — different axes of change. A PDF feature must not touch billing. No 3000-line god file.
- SHARED CORE, THIN ADAPTERS — one business logic; Telegram/CLI/desktop is a shell (I/O + auth + UX). A polish bug is fixed in one place, both clients stay fine.
- STOP WHEN THE NEXT ABSTRACTION DOESN'T PAY RENT THIS WEEK — an abstraction must pay for itself now, not "someday".
2. Config and evolution
- CONFIG OUTSIDE REPO, DEFAULTS IN CODE — secrets and ops tuning never in git; safe defaults in code; override via env.
- SCHEMA EVOLUTION MUST NOT WIPE PROD — deploy must not require DROP TABLE: CREATE IF NOT EXISTS + ALTER ADD COLUMN ignore-if-exists.
- FEATURE FLAG/ENV DEFAULT > REWRITE — ops tuning via flag/env, not rewriting.
- DETERMINISTIC REBUILD > STALE CACHE — rebuilding deterministically beats living with a stale cache.
3. Code patterns
- EXPLICIT SPEND ORDER IN ONE FUNCTION — the debiting order (free→bonus→paid) is one algorithm in one place.
- FALLBACK CHAIN FOR PROVIDERS — one vendor = SPOF: ordered list; next on timeout/5xx; fail only when all are dead.
- PURE FUNCTIONS FOR ASSEMBLE/EXPORT; IMPURE AT THE EDGES — assembly/export are pure functions; I/O at the boundaries.
- MAKE ILLEGAL STATES UNREPRESENTABLE — separate fields over boolean soup:
status: active|finishedinstead of flags. - COMMENTS EXPLAIN WHY AND CEILING — not what the line does, but why and what ceiling.
- DELETE DEAD CODE; DON'T COMMENT IT OUT FOREVER — dead code gets removed.
- NAMING: VERBS THAT MEAN $ — charge_seconds, apply_referral, can_afford — verbs with money semantics.
- FLOAT MONEY IS EVIL LONG-TERM — money is not float; minutes are fine if consistent + tested.
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.
- 2d ago First seen · 57 lines · 119 tokens per session scan A 10c03e847dbb
architecture-simplicity is a skill published in the GitHub repository oleg494/coding-kit (1 stars, last pushed 2d ago), licensed MIT. It adds 119 tokens to every session and 1,013 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
run
Execute a named agent role with optimized instructions. Explicit invocation only ($run). Never trigger implicitly.
tip
Deliver a transformative life perspective shift and a productivity tip. Use when the user invokes /tip or wants non-technical inspiration or a fresh mental model.
agentic-production-readiness
Prepare an AI agent system for production operation. Cover SHIELD controls, sandbox/canary/production rollout, OpenTelemetry observability with GenAI semantic conventions, Agent Card drafting, governance, and post-deploy monitoring. Use for production readiness checks, go-live checklists, agent monitoring, agent…
agentic-security-review
Run a security and dependency audit for agent systems, tool-using AI apps, MCP/A2A integrations, or security-sensitive AI-generated code. Check slopsquatting risk, tool shadowing, rug pulls, memory/context poisoning, secrets, unsafe permissions, and common CWE patterns. Use when asked for security review, dependency…
agentic-spec
Create a structured specification before agentic coding work. Assemble the six context types, scale rigor for prototype/internal/production tasks, produce SPEC.md, and configure focused AGENTS.md boundaries. Use when asked to write a spec, plan a feature, design an agent/system, define architecture, or create…
agentic-evals
Design evaluation contracts and test plans for agentic systems. Create deterministic tests, trajectory evals, quality dimensions, gold-set criteria, and CI gates before or after implementation. Use when asked for tests first, an eval plan, success criteria, non-deterministic testing, LLM-as-judge setup, or…