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 QuentinCody/interlinked-cli --skill interlinked-semantic-indexgit clone --depth 1 https://github.com/QuentinCody/interlinked-cliWrote 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/quentincody/interlinked-cli/interlinked-semantic-index)<a href="https://agentmods.dev/skills/quentincody/interlinked-cli/interlinked-semantic-index"><img src="https://agentmods.dev/badge/skills/quentincody/interlinked-cli/interlinked-semantic-index/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/quentincody/interlinked-cli/interlinked-semantic-index"><img src="https://agentmods.dev/badge/skills/quentincody/interlinked-cli/interlinked-semantic-index.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 | $0.00075 | $0.01922 |
| Opus 5.5 | $0.00030 | $0.00769 |
| Sonnet 5.5 | $0.00015 | $0.00384 |
| Haiku 4.5 | $0.00007 | $0.00192 |
Grade A, and why
interlinked-semantic-index 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 7d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
interlinked-semantic-index — local function retrieval
Separate decision-metrics research index
metrics decisions embed|geometry|retrieve|candidates uses a separate Ollama pipeline
under .interlinked/decision-metrics/; it does not reuse or change semantic.json,
the GGUF manifest, or index/functions/. Load interlinked-quality-gates for its
measurement, ledger and audit commands. retrieve defaults to BM25; embedding and
hybrid modes are explicit. Historical neighbors require fix provenance and exclude
future data; current-consumer candidate discovery retains retrieval misses.
geometry takes at most 200 records with one pinned embedding identity, retaining
uncalibrated churn, group dispersion and nearest-neighbor distances. It is not a
quality score; supply the same model identity for any prior embedding.
The default is the full embeddinggemma-2:740m-bf16, with all encoders retained and
768-dimensional output. Retrieval uses Google's code-query/document prompts;
geometry uses symmetric similarity prompts. Profile identity travels with the
model digest; do not mix those populations. Requests use 8K context and reject
truncation. Ollama 0.35.1 cannot pull this model; use a compatible newer runtime.
The current evidence path is text; selecting full weights does not certify image
or audio ingestion. Qwen remains available by explicit embeddingModel config.
The decision runtime serializes cooperating local jobs, checks resident models,
switches between the two configured models and unloads after each stage. It refuses
unrelated resident models. Embeddings are cached by exact input and model digest;
they are retrieval/ranking evidence, not calibrated quality probabilities. The
short PostToolUse advisory path does not perform repository-wide retrieval.
See docs/decision-metrics.md for budgets and explicit remote decision configuration;
the existing semantic commands below remain local-only.
Interlinked can embed complete functions into a repository-local vector index and search them by meaning or similarity. The v1 subsystem is experimental, explicit, and local-only: no source, query, vector, or model inference is sent to the Interlinked MCP Server or a cloud provider.
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.
- 7d ago Changed · +27 lines 8b51a57502d4
- 1mo ago Changed · +17 lines 163950d05360
- 1mo ago First seen · 97 lines · 75 tokens per session scan A beacc0690914
interlinked-semantic-index is a skill published in the GitHub repository QuentinCody/interlinked-cli (180 stars, last pushed yesterday), licensed MIT. It adds 75 tokens to every session and 1,922 once invoked, about $0.0003 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 2026-09-04.
Other skills, from other repositories
embeddings
Vector embeddings with HNSW indexing, sql.js persistence, and hyperbolic support. 75x faster with agentic-flow integration. Use when: semantic search, pattern matching, similarity queries, knowledge retrieval. Skip when: exact text matching, simple lookups, no semantic understanding needed.
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
9router-embeddings
Generate vector embeddings via 9Router /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia / GitHub embedding models for RAG, semantic search, similarity. Use when the user wants embeddings, vectors, RAG, semantic search, or to embed text.
similarity-search-patterns
Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.
embedding-strategies
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.