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 skill-authoringgit 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/skill-authoring)<a href="https://agentmods.dev/skills/damianvtran/local-operator/skill-authoring"><img src="https://agentmods.dev/badge/skills/damianvtran/local-operator/skill-authoring/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/skill-authoring"><img src="https://agentmods.dev/badge/skills/damianvtran/local-operator/skill-authoring.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 | $0.00043 | $0.00646 |
| Opus 5.5 | $0.00017 | $0.00258 |
| Sonnet 5.5 | $0.00009 | $0.00129 |
| Haiku 4.5 | $0.00004 | $0.00065 |
Grade A, and why
skill-authoring 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 5d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill authoring
A skill is instructions that route: the description selects it, the body runs it. Write for both, and test before shipping.
Structure
SKILL.mdfrontmatter:name(kebab-case, equal to the directory name) anddescription. Flags and loading rules:guide://extensions.- Body: the procedure, imperative, in the fewest lines that stay complete. Lead with the steps; put the why in one clause where a step would look arbitrary without it.
- References (
references/*.md, at most 3): deeper material only some tasks need. The body must stand alone without them. Template:references/template.md. - Budgets: description 220 characters or less; body 120 lines and about 6 KB or less. Every session lists the description, so cut hard.
The description is the routing signal
- It is the only text seen before a skill is read. It must contain the task vocabulary a user would actually type.
- Third person, one or two sentences: what the skill does, then "Use when ..." for the trigger.
- Test it: write three prompts that should select the skill and two that should not. If the description cannot separate them, rewrite it.
Body rules
- Imperative voice; checklists and tables over prose.
- Add a red-flags section wherever the failure mode is an agent rationalising a shortcut; those are the costly failures.
- State constraints where they matter ("never install a browser engine", budgets, portability rules).
- Do not restate what the model already knows, and do not duplicate agent role instructions; skills are shared knowledge, roles are assignments.
Test before shipping
- Dry-run: hand the skill and a realistic task to a fresh agent context; watch whether the procedure is followable as written. Ambiguity shows up as invented steps.
- Pilot prompts: selection fires on the should-list and stays quiet on the should-not-list.
- Budget check: measure description characters, body lines, and bytes mechanically after every edit.
Improvement loop
Fix a repeated mistake at the HIGHEST enforceable level: lint, then test, then prose. A rule in tooling cannot be forgotten; a rule in prose can.
What ships with it
1 file 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.
- 5d ago First seen · 52 lines · 43 tokens per session scan A 84556a4a4d28
skill-authoring is a skill published in the GitHub repository damianvtran/local-operator (218 stars, last pushed today), licensed MIT. It adds 43 tokens to every session and 646 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.