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 damianvtran/local-operator --skill engineering-principlesgit clone --depth 1 https://github.com/damianvtran/local-operatorWrote 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/damianvtran/local-operator/engineering-principles)<a href="https://agentmods.dev/skills/damianvtran/local-operator/engineering-principles"><img src="https://agentmods.dev/badge/skills/damianvtran/local-operator/engineering-principles/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/damianvtran/local-operator/engineering-principles"><img src="https://agentmods.dev/badge/skills/damianvtran/local-operator/engineering-principles.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 | $0.00042 | $0.00619 |
| Opus 5.5 | $0.00017 | $0.00248 |
| Sonnet 5.5 | $0.00008 | $0.00124 |
| Haiku 4.5 | $0.00004 | $0.00062 |
Grade A, and why
engineering-principles 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 3d 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Engineering principles
Judgement for building changes. One rule per line; the third column is what breaking it looks like.
| Principle | In practice | Violated by |
|---|---|---|
| Laziness protocol | Do not build what nothing needs yet. | Speculative abstraction, config for a case nobody has |
| Smallest change | The best change leaves the least to review, test, and revert. | Drive-by refactors mixed into a fix |
| Subtract before adding | Delete a concept before you add one; every new layer is paid for forever. | A new wrapper around an old wrapper |
| Data structures before logic | Get the shape of the data right and the code collapses into simple reads. | Nested conditionals over a badly shaped object |
| Boundary discipline | Validate at the edges (user input, network, files); trust the interior. | Re-validating everywhere, or validating nowhere |
| Type system discipline | Make illegal states unrepresentable where the language allows it. | Runtime flags that contradict each other |
| Idempotency | Running it twice is as safe as running it once. | Operations that double-charge, double-post, or duplicate |
| Migrate then delete | Expand, migrate callers, contract; the old path goes in the same change. | "Deprecated" code left for a ticket that never comes |
| Foundations before features | Verify the facts the design rests on before building on them. | A feature built on an unmeasured assumption |
| Encode lessons in structure | After the same bug twice, change the code or tooling so it cannot recur. | A comment saying "be careful" |
| Highest enforceable level | Fix at the strongest level available: lint, then test, then prose. | A wiki page about the rule being broken |
| Experience first | The user-visible result decides; internal elegance is a cost, not a product. | Refactors with no observable change |
| Delete dead weight | Unused, unreachable, and commented-out code is a claim nobody checks. | "We might need it"; version control remembers |
Costly evidence preflight
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.
- 3d ago Changed · +9 lines b9053a3f1999
- 5d ago First seen · 30 lines · 42 tokens per session scan A f8266cb52a07
engineering-principles is a skill published in the GitHub repository damianvtran/local-operator (218 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 619 once invoked, about $0.0002 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 2026-10-11.
Other skills, from other repositories
building-agents
Use when building or restructuring an LLM agent — provider adapter, tool calling, structured output, RAG, agent loop, eval gate, cost routing, tracing, MCP server — model-agnostic across OpenAI/Anthropic/Gemini/OSS so a model swap is a config change. NOT vector-store SQL alone (that is postgresdb) or service…
agent-eval
Use when measuring whether an LLM or agent system actually got better and gating merges on it: golden sets, fixing an inflated LLM-as-judge, scoring RAG (faithfulness, contextual recall) or agent trajectories (tool correctness, completion), or picking an eval framework. NOT building the agent loop, tools or RAG…
prompt-engineering
Use when one prompt must give the same right answer across reruns, models, and pasted-in hostile input: forcing a fixed schema, picking the few-shot set, ordering the prompt blocks, or the inline cases you run while tuning. NOT the agent loop, tools, or retrieval (that is building-agents), NOT a standing CI eval…
coding-standards
Applies language-neutral engineering standards when writing or reviewing code, especially around boundaries, failures, domain models, dependencies, tests, and type safety.
domain-modeling
Maintains project domain language, context maps, diagrams, and architectural decisions under ai-artifacts. Use when clarifying terminology, bounded contexts, or durable design decisions.
setup-goal
Turns an idea into an approved goal package under ai-artifacts. Use when work needs clarified intent, scope, accepted facts, an implementation plan, and an explicit handoff.