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 AnthonyAlcaraz/agentic-graph-rag-skills --skill homoiconic-meta-schemagit clone --depth 1 https://github.com/AnthonyAlcaraz/agentic-graph-rag-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/anthonyalcaraz/agentic-graph-rag-skills/homoiconic-meta-schema)<a href="https://agentmods.dev/skills/anthonyalcaraz/agentic-graph-rag-skills/homoiconic-meta-schema"><img src="https://agentmods.dev/badge/skills/anthonyalcaraz/agentic-graph-rag-skills/homoiconic-meta-schema/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/anthonyalcaraz/agentic-graph-rag-skills/homoiconic-meta-schema"><img src="https://agentmods.dev/badge/skills/anthonyalcaraz/agentic-graph-rag-skills/homoiconic-meta-schema.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 | $0.00227 | $0.02165 |
| Opus 5 | $0.00113 | $0.01082 |
| Sonnet 5 | $0.00045 | $0.00433 |
| Haiku 4.5 | $0.00023 | $0.00216 |
Grade A, and why
homoiconic-meta-schema 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 12d 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Homoiconic Meta-Schema
Overview
Agent-friendly knowledge graphs need homoiconicity: code and data in the same representation, so agents can inspect and modify their own operational logic. Ch3 gives two constructs.
Meta-knowledge structures (Example 3-6). A metaschema describes the schema
itself — it defines what an EntityType is (a name, a description, a list of
property definitions). Then domain knowledge is stored using the same
representation: a Person entity-type is just data with name, birth_date,
occupation properties. The syntax of schema and data is identical. This skill
runs the same validation at both levels: validate_entity_type checks a type
against the metaschema; validate_data_against_type checks an instance against
its type. Same machinery, two levels — that is the homoiconic property doing
real work. It lets agents reason about knowledge completeness, dynamically
update schemas as they learn, and self-evolve without external reprogramming.
Executable knowledge patterns (Example 3-7). Operational rules become
first-class graph entities. A Rule has descriptive metadata, a condition
(graph pattern match), and an action (tiered WHEN ... THEN SET ... /
ELSE). Because the rule is data, agents can reason about rules, not just
follow them — discover, modify, create rules, and explain decisions by citing
the rule. This skill parses the tiered action, validates the rule has a
parseable clause, and evaluates it in source order against facts
(DetermineCustomerSegment: 25 purchases -> Premium, 15 -> Regular, 3 ->
Basic). The DevOps OperationalRule (ValidateProductionDeployment) is the
same construct applied to infrastructure.
When to Use
- Building agents that reason about or modify their own schema (Ch7 self-evolution)
- Storing business/operational rules as queryable graph data, not hidden code
- Validating agent-proposed schema extensions before applying them
- Representing the ontology itself as data the agent can query
What ships with it
2 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.
- 12d ago First seen · 151 lines · 227 tokens per session scan A a82fa88ded45
homoiconic-meta-schema is a skill published in the GitHub repository AnthonyAlcaraz/agentic-graph-rag-skills (10 stars, last pushed 2mo ago), licensed MIT. It adds 227 tokens to every session and 2,165 once invoked, about $0.0011 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 2026-08-31.
Other skills, from other repositories
graphify
Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community…
lemmalog
Externalize working memory and logical state into the lemmalog Datalog engine (MCP). Use for ANY multi-step task where state should outlive one context window or span agents: long investigations, debugging sessions, audits, multi-agent searches, systematic explorations, planning with many interdependent constraints…
jurisd-research
Expert Australian/NZ legal research and AGLC4 citation using the jurisd MCP server. Use when finding cases or legislation (AustLII), looking up a provision offline, formatting or resolving citations, building a pinpoint, tracing who-cites-what, or producing an AGLC4 bibliography. Triggers on case law, legislation…
repo_search
Search repository text through a deterministic first-class fak command.
container-manager-kg-ingestion
Snapshot a host's Docker/Podman/Swarm inventory into the epistemic-graph knowledge graph as typed OWL nodes via the container-manager-mcp MCP server — containers, images, volumes, networks, swarm services and nodes, with their :usesImage / :runsOn / :builtFrom links. Use when the agent must record live container state…
cortex-design
Use this skill to generate well-branded interfaces and assets for Cortex, either for production or throwaway prototypes/mocks/etc. Contains essential design guidelines, colors, type, fonts, assets, and UI kit components for prototyping.