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 LLM-Coding/Semantic-Anchors --skill semantic-anchor-translatorgit clone --depth 1 https://github.com/LLM-Coding/Semantic-AnchorsWrote 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/llm-coding/semantic-anchors/semantic-anchor-translator)<a href="https://agentmods.dev/skills/llm-coding/semantic-anchors/semantic-anchor-translator"><img src="https://agentmods.dev/badge/skills/llm-coding/semantic-anchors/semantic-anchor-translator/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/llm-coding/semantic-anchors/semantic-anchor-translator"><img src="https://agentmods.dev/badge/skills/llm-coding/semantic-anchors/semantic-anchor-translator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00094 | $0.00887 |
| Opus 5.5 | $0.00038 | $0.00355 |
| Sonnet 5.5 | $0.00019 | $0.00177 |
| Haiku 4.5 | $0.00009 | $0.00089 |
Grade A, and why
semantic-anchor-translator 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 22d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Semantic Anchor Translator
Translate between natural language and established terminology that activates rich knowledge domains.
What are Semantic Anchors?
Semantic anchors are well-defined terms, methodologies, and frameworks that serve as reference points when communicating. They act as shared vocabulary that triggers specific, contextually rich knowledge.
Example: Instead of "write tests first, mock dependencies, work from outside-in" → say "TDD, London School"
Two Modes
Recognition Mode (verbose → anchor)
When user describes something like:
- "I want to categorize things so they don't overlap and cover everything"
- "I need to structure docs into tutorials, how-tos, explanations, and reference"
- "Start with the conclusion, then give supporting details"
Respond with the anchor term + brief validation:
You're describing MECE Principle (Mutually Exclusive, Collectively Exhaustive).
Guidance Mode (question → anchors)
When user asks for direction:
- "How should I document architecture decisions?"
- "What's a good way to prioritize requirements?"
- "How do I debug this systematically?"
Suggest relevant anchors:
For architecture decisions: ADR according to Nygard or MADR. Both provide lightweight templates for capturing context, decision, and consequences.
Response Pattern
- Identify the anchor (or 2-3 if ambiguous)
- One-sentence explanation of why it matches
- Optional: related anchors they might also find useful
- If unsure: ask clarifying question
Keep responses concise — the value is precision, not explanation.
Catalog Reference
Full catalog with categories, roles, and core concepts: references/catalog.md
Browse online: https://llm-coding.github.io/Semantic-Anchors/
Quick Category Index
| Category | Key Anchors |
|---|---|
| Testing & Quality | TDD Chicago/London, BDD, Gherkin, Test Double (Meszaros + 5 subtypes), Testing Pyramid, Mutation Testing, Property-Based Testing, Fagan Inspection, STRIDE, LINDDUN, LLM-Evaluations |
| Software Architecture | Clean Architecture, Hexagonal, DDD, EDA, CQRS, VSA, arc42, C4, ADR, MADR, ATAM, LASR, ISO 25010, OWASP Top 10 |
| Design Principles | SOLID (+ 5 individual), GRASP, CRC-Cards, GoF Patterns (23 patterns), Fowler PEAA, DRY, KISS, SPOT, SSOT, YAGNI |
| Problem-Solving | Five Whys, Feynman Technique, Rubber Duck, Devil's Advocate, Morphological Box, Chain of Thought, Cynefin |
| Requirements | INVEST, PRD, MoSCoW, EARS, User Story Mapping, JTBD, Impact Mapping, Problem Space NVC |
| Communication | BLUF, Pyramid Principle, MECE, Gutes Deutsch, Plain English, Chatham House Rule, Socratic Method, MBTI |
| Documentation | P.A.R.A., Diátaxis, Docs-as-Code |
| Development Workflow | GTD, Definition of Done, GitHub Flow, Conventional Commits, Effective Go, SemVer, BEM, Mikado Method, Hemingway Bridge |
| Statistical Methods | SPC, Control Chart, Nelson Rules |
| Strategic Planning | Wardley Mapping, Pugh Matrix, SWOT, PERT |
| Creative Writing | Three-Act Structure, Hero's Journey, Save the Cat!, Fichtean Curve, Freytag's Pyramid, Story Circle, Kishōtenketsu |
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.
- 22d ago Changed bebeb9f1c18a
- 1mo ago First seen · 73 lines · 94 tokens per session scan A 4e562d836a27
semantic-anchor-translator is a skill published in the GitHub repository LLM-Coding/Semantic-Anchors (521 stars, last pushed 3d ago), licensed Apache-2.0. It adds 94 tokens to every session and 887 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
tome
Converting technical knowledge into durable learning documents and publishable articles. Use for diff-based teaching, decision records, onboarding, note/Zenn/Qiita/dev.to posts, article series, retrospectives, and cross-platform repurposing.
kumihimo-retro
Fold the build journal's lessons back into the skills, CLAUDE.md, and CONVENTIONS.md — the "training" pass for this repo's Claude tooling. Use at each milestone close, after every 10 iterations, or when Thomas invokes /kumihimo-retro. One retro is one commit.
agent-teacher
A teaching aid that explains technical ideas with a small runnable code example and a guided walkthrough. It is meant for learning how something works, not fixing existing code.
ai-engineering-toolkit
Overview of six AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
prompt-master
Generates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt a prompt for a specific AI tool (LLM, Cursor, Midjourney, image AI, video AI, coding agents, etc.). Does not activate for general conversation, coding tasks, document writing, or other…
flux2-lora-training
Plan or review LoRA and edit-training work specifically for FLUX.2 Klein or Qwen-Image-Edit, including paired datasets, trainer-version contracts, and held-out fidelity checks. Do not use for generic Stable Diffusion/DiT training, prompt authoring, or model serving; route those tasks to their specialized skill.