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/anthonysuherli/br8n/schemanpx skills add anthonysuherli/br8n --skill schemagit clone --depth 1 https://github.com/anthonysuherli/br8nWrote 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/anthonysuherli/br8n/schema)<a href="https://agentmods.dev/skills/anthonysuherli/br8n/schema"><img src="https://agentmods.dev/badge/skills/anthonysuherli/br8n/schema.svg" alt="Measured on agentmods" 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 | $0.00101 | $0.01104 |
| Opus 5 | $0.00051 | $0.00552 |
| Sonnet 5 | $0.00020 | $0.00221 |
| Haiku 4.5 | $0.00010 | $0.00110 |
Grade A, and why
schema scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
br8n — Schema (the guided seam)
br8n maintains itself silently; structure is the one thing it won't change without you. This skill is that seam: it checks whether the KB's knowledge-graph ontology still fits what's been collected, and — only when warranted — co-designs a new one with you, one question at a time. Everything else (capture, distill, graph population) happens in the background; here you manage the shape.
Target (same convention as every br8n skill):
project= current git repo name —basename "$(git rev-parse --show-toplevel)"kb= current git branch —git rev-parse --abbrev-ref HEAD
Step 1 — Read the drift verdict
Call mcp__plugin_br8n_br8n__br8n_schema_drift(project, kb). It reads the
built graph's type distribution against the approved schema (no LLM cost) and returns:
mode—cold_start|drift|ok|empty(|offif the gate is disabled).should_offer— whether this is worth surfacing now (debounced; a declined offer doesn't re-nag until drift intensifies).offer_line— the ready-to-show one-liner (null unlessshould_offer).residual/ratio/residual_types— the off-ontology cluster: the entities the current schema couldn't place. This is the seed the wizard reshapes around.
Route on mode:
| mode | what it means | do |
|---|---|---|
empty |
graph too small to judge | tell the user there isn't enough yet; suggest /br8n:capture / /br8n:explore. Stop. |
ok |
the ontology still fits | report "schema v{n} still fits ({residual}/{node_count} unplaced)". Stop unless the user explicitly wants to reconfigure anyway. |
cold_start |
enough collected, no schema yet | go to Step 2 (first-run flow). |
drift |
schema set, reality moved past it | go to Step 2 (reconfigure flow), leading with the residual cluster. |
If the user invoked /br8n:schema explicitly, proceed to Step 2 even when
should_offer is false — the user opted in directly. If this skill was reached from
a surfaced offer, only proceed when the user accepts.
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.
- 5d ago First seen · 77 lines · 101 tokens per session scan A 50ec904ca655
schema is a skill published in the GitHub repository anthonysuherli/br8n (1 stars, last pushed 1mo ago), licensed MIT. It adds 101 tokens to every session and 1,104 once invoked, about $0.0005 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
visualize
Visualize the Semantica knowledge graph — topology, centrality, communities, paths, embeddings, decision insights, and temporal evolution. Uses GraphAnalyzer, CentralityCalculator, CommunityDetector, PathFinder, and ContextGraph analytics. Sub-commands: topology, centrality, community, path, decision-graph, insights…
embed
Generate, inspect, and use node/text embeddings in Semantica — compute Node2Vec embeddings, find similar nodes, score link predictions, batch similarity, and pairwise similarity. Uses NodeEmbedder, SimilarityCalculator, LinkPredictor, and AgentContext. Sub-commands: compute, similar, similarity, predict-link…
reason
Run reasoning over the Semantica knowledge graph — deductive logic, abductive hypothesis generation, Datalog programs, SPARQL queries, Rete network evaluation. Uses DeductiveReasoner, AbductiveReasoner, DatalogReasoner, SPARQLReasoner, ReteEngine. Sub-commands: deductive, abductive, datalog, sparql, rete, prove…
validate
Validate Semantica pipelines, extraction quality, graph schemas, and ontology consistency. Returns structured error/warning checklists. Uses PipelineValidator, PipelineBuilder.validatepipeline(), GraphValidator, and OntologyValidator. Sub-commands: pipeline, step, dependencies, extraction, graph, ontology, performance.
temporal
Temporal graph operations on Semantica — scoped queries at a point in time, graph snapshots, node change timelines, temporal causal analysis, and graph state reconstruction. Uses AgentContext.findprecedents(asof=), ContextGraph.stateat(), CausalChainAnalyzer.traceattime(), and TemporalQueryRewriter. Sub-commands…
extract
Run the full Semantica semantic extraction pipeline on a file or selected text — NER, relations, events, coreference resolution, triplets, and validation. Clears result cache before each run. Returns Markdown tables with entity/relation/event/triplet results and inline validator warnings.