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 SkardiLabs/skardi-skills --skill graph-sourcegit clone --depth 1 https://github.com/SkardiLabs/skardi-skillsWrote 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/skardilabs/skardi-skills/graph-source)<a href="https://agentmods.dev/skills/skardilabs/skardi-skills/graph-source"><img src="https://agentmods.dev/badge/skills/skardilabs/skardi-skills/graph-source/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/skardilabs/skardi-skills/graph-source"><img src="https://agentmods.dev/badge/skills/skardilabs/skardi-skills/graph-source.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 | $0.00172 | $0.01782 |
| Opus 5 | $0.00086 | $0.00891 |
| Sonnet 5 | $0.00034 | $0.00356 |
| Haiku 4.5 | $0.00017 | $0.00178 |
Grade A, and why
graph-source 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 today.
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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Connecting a graph source to Skardi
You are wiring a property graph into Skardi as SQL tables. Skardi does
not parse or store graphs — the graph engine (Apache AGE: openCypher
inside Postgres) owns storage and traversal; Skardi forwards read-only
Cypher and maps results into Arrow rows with a planning-time-stable
schema. Design: docs/superpowers/specs/2026-08-08-graph-engine-bypass-design.md
in the skardi repo; operational truth:
docs/graph.md
there. When this skill and those documents
disagree, the documents win — check them, then fix this skill.
Version prerequisite: this is a preview skill for Skardi main, verified
against commit 1f2ecae. Clone that revision and run
cargo build --release -p skardi-server; v0.5.0 has neither type: graph
sources nor the cypher_query / graph_schema UDTFs. The preview backend is
AGE (milestone status M4 — YAML catalog views and pipeline parameter
passthrough). Neo4j and Kuzu are later milestones: the config carries a
backend: field for them, but do not write configuration or guidance for a
backend that has no implementation. Milestone one is read-only end to end;
write paths are deferred by design.
The reason this skill exists: every trap below is real, was hit, and is
documented — but scattered. The two that cost the most debugging time:
the ad-hoc columns argument binds positionally (two same-typed
columns declared out of RETURN order swap silently — no error, wrong
data), and a view's SQL WHERE does not push into its Cypher (a
query that wants one row still fails RowCapExceeded if the view is
unbounded). Both are invisible until they bite.
The workflow
Work the phases in order. Each phase names its reference file — read it before doing that phase's work, not after it goes wrong.
Phase 1 — Provision the backend
What ships with it
4 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.
- today Changed · +2 lines a0559f22de7b
- 6d ago First seen · 148 lines · 172 tokens per session scan A 27f4914c64d4
graph-source is a skill published in the GitHub repository SkardiLabs/skardi-skills (5 stars, last pushed today), licensed Apache-2.0. It adds 172 tokens to every session and 1,782 once invoked, about $0.0009 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 2026-09-03.
Other skills, from other repositories
pgvector-semantic-search
Use this skill for setting up vector similarity search with pgvector for AI/ML embeddings, RAG applications, or semantic search. Trigger when user asks to: Store or search vector embeddings in PostgreSQL Set up semantic search, similarity search, or nearest neighbor search Create HNSW or IVFFlat indexes for vectors…
postgres-hybrid-text-search
Use this skill to implement hybrid search combining BM25 keyword search with semantic vector search using Reciprocal Rank Fusion (RRF). Trigger when user asks to: Combine keyword and semantic search Implement hybrid search or multi-modal retrieval Use BM25/pgtextsearch with pgvector together Implement RRF (Reciprocal…
ai-vector-brain
Builds vector-brain implementations for repos, docs hubs, and compliance corpora. Use when creating pgvector retrieval brains with scripts, SQL, manifests, and evals.
postgres-semantic-search
PostgreSQL-based semantic and hybrid search with pgvector and ParadeDB. Use when implementing vector search, semantic search, hybrid search, or full-text search in PostgreSQL. Covers pgvector indexing, hybrid FTS/BM25 + RRF, ParadeDB, reranking, halfvec, multilingual search, query translation, and domain evals.…
vector-db-rag-expert
Expert guide for high-performance Vector Databases, RAG architectures, pgvector HNSW indexing, hybrid search (Dense + BM25), and semantic chunking / Panduan ahli Vector DB, arsitektur RAG, pgvector HNSW, dan hybrid search.
laravel-vector-search
Use when implementing semantic/vector search in Laravel 13 with PostgreSQL + pgvector.