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/production-first-decisionsnpx skills add oleg494/coding-kit --skill production-first-decisionsgit 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 | $0.00115 | $0.00704 |
| Opus 5 | $0.00057 | $0.00352 |
| Sonnet 5 | $0.00023 | $0.00141 |
| Haiku 4.5 | $0.00012 | $0.00070 |
Grade A, and why
production-first-decisions 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Production-first: decisions by industry practice, not from your head
The source of truth is the industry; knowledge is a hypothesis until verified.
Workflow (order of application)
- Formulate the question "how is this done in production?" — explicitly, before any action.
- Web search: 5-10 queries from different angles — manuals, official guides, GitHub, practitioner articles, ADRs. Primary sources, not retellings.
- Cross-check YOUR hypothesis against what you found. Your own knowledge is only an assumption; web search is source of truth #1. "Thought it through" without searching = a guess, not a decision.
- Do it the industry way. Readiness criterion for a decision: "everyone does it this way, not just me alone." Not confirmed by sources → it's a hypothesis: verify by search before writing code.
Test-before-integration (spike → ADR)
A new tool/library/approach — FIRST benchmark, THEN integration:
- Question: what are we checking — functionality, fit to the stack?
- Benchmark in a sandbox: install it, run a real case, compare with alternatives AND with "doing nothing" (doing nothing is always an option).
- Record the conclusion in Wiki/decisions/: what was chosen, what was rejected, the benchmarks.
- Integrate only after proof. Without a benchmark, integration is a guess.
Research depth — by task
- Reference (syntax, command) — 2-3 sources, one pass.
- Decision/choice — DEEP research: breadth (5-10 queries in parallel), then depth; canonical repos, PRs, issues, ADRs; "everyone does it" — measure (how many production projects actually do), not feel.
Three decision principles (filter before code)
- DRY — one piece of logic and one piece of knowledge in one place. Duplication = two places that must change together.
- KISS — the simpler option, if it closes the task. Complexity is justified when the simple one can't cope, not "for the future".
- YAGNI — don't build what wasn't asked for. "Might come in handy" is an insufficient reason.
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 · 46 lines · 115 tokens per session scan A 6aecd50f9118
production-first-decisions is a skill published in the GitHub repository oleg494/coding-kit (1 stars, last pushed 3d ago), licensed MIT. It adds 115 tokens to every session and 704 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…