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/longbkit/clisbot/naming-expertnpx skills add longbkit/clisbot --skill naming-expertgit clone --depth 1 https://github.com/longbkit/clisbotWhat 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 | $0.00125 | $0.01911 |
| Opus 5 | $0.00063 | $0.00955 |
| Sonnet 5 | $0.00025 | $0.00382 |
| Haiku 4.5 | $0.00013 | $0.00191 |
Grade A, and why
naming-expert 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 — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Naming expert
Treat naming as architecture. Make each name reveal the concept, owner, role, scope, and expected behavior with the least reader inference. Replace model memory with a repeatable loop: observe, inventory, compare, decide, ratify, and enforce.
Select one mode
State the selected mode and scope before acting. Do not blend modes silently.
- Use
planfor a naming proposal, roadmap, migration design, or broad rename. Create a dated supporting artifact in the repository location selected by audit-format.md. Do not edit product code or claim a canonical decision. - Use
decidewhen the user asks to choose, accept, ratify, or establish the canonical name. Record the accepted definition in the smallest canonical language or convention owner and create or update the appropriate decision record when the choice is material. Perform a code-wide rename only when the user also asks to implement it. - Use
reviewfor a naming audit, code review, diff review, or consistency check. Review is read-only unless the user separately asks to fix findings. - If no signal is clear, default to
review.
Read audit-format.md before creating or updating a persistent naming artifact.
Ground the current language
- Read the nearest repository instructions and establish the dirty-tree boundary.
- Start with
docs/architecture/domain-language.mdfor canonical concepts and ownership, thendocs/architecture/naming-conventions.mdfor repository representations. - Read the relevant architecture owner, feature front door, public CLI/help, config schema, persistence contract, or runner/channel contract for the requested scope.
- Treat architecture and accepted decisions as normative. Treat feature docs, guides, audits, research, tasks, and Git history according to repository precedence; do not let historical wording override current contracts.
- Preserve unrelated user changes and check existing tests or machine gates before inventing another naming rule.
What ships with it
3 files 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.
- 3d ago First seen · 203 lines · 125 tokens per session scan A 269f2a327846
naming-expert is a skill published in the GitHub repository longbkit/clisbot (114 stars, last pushed 3d ago), licensed MIT. It adds 125 tokens to every session and 1,911 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 2026-08-30.
Other skills, from other repositories
chatbot
Use when a support or sales bot on a live website must behave: persona/system prompt, grounding so it cannot invent prices or policy, jailbreak and injection defense, the human handoff, launch metrics and kill switch. NOT the agent loop or RAG index under it (that is building-agents), NOT a human answering one ticket…
create-ppt
Creates polished PowerPoint presentations with dark-first design, custom palettes, charts, and tables. Use when creating, designing, or generating PPTX slide decks or presentations.
create-pdf
Guidelines for creating polished, themed PDF reports with the code execution tool.
skill-authoring-best-practices
Best practices for writing effective Skills that are discoverable, concise, and reliable. Use when creating, reviewing, or improving Skills.
cloud_storage
Skill for uploading and downloading files from cloud storage (AWS S3 or Azure Blob Storage).
sandbox_file_manager
Use this skill when you need to manage files inside the active remote or local sandbox, including listing sandbox files, downloading files from the sandbox to the local backend, or uploading local backend files to the sandbox.