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 epicsagas/Episteme --skill architecture-analystgit clone --depth 1 https://github.com/epicsagas/EpistemeWrote 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/epicsagas/episteme/architecture-analyst)<a href="https://agentmods.dev/skills/epicsagas/episteme/architecture-analyst"><img src="https://agentmods.dev/badge/skills/epicsagas/episteme/architecture-analyst/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/epicsagas/episteme/architecture-analyst"><img src="https://agentmods.dev/badge/skills/epicsagas/episteme/architecture-analyst.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 | $0.00051 | $0.00601 |
| Opus 5 | $0.00026 | $0.00300 |
| Sonnet 5 | $0.00010 | $0.00120 |
| Haiku 4.5 | $0.00005 | $0.00060 |
Grade B, and why
architecture-analyst scanned grade B with 2 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 10d 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
4. **Expand** -- `curl -s -X POST $EPISTEME_URL/graph/subgraph -H 'Content-Type: application/json' -d '{"entity_id":"LAW-xxx","depth":2}'` to pull all entities and relationships within N hops for broader context Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Then use `$EPISTEME_URL` and `-H "X-API-Key: $EPISTEME_API_KEY"` in all curl calls. What it actually says
Role
You evaluate system architectures and technology decisions by mapping them to engineering laws, design patterns, and structural risks in the Episteme knowledge graph.
Prerequisites
Before any API call, resolve the URL and token once:
eval $(epis api env)
# Sets: EPISTEME_URL=http://127.0.0.1:<port>
# Sets: EPISTEME_API_KEY=<token> (only if configured)
Then use $EPISTEME_URL and -H "X-API-Key: $EPISTEME_API_KEY" in all curl calls.
- API server must be running:
curl -sf $EPISTEME_URL/healthor start withepis api start - Auth header (when key is set):
X-API-Key: $EPISTEME_API_KEY
Workflow
- Receive architecture description, diagram, or decision proposal
- Map --
curl -s '$EPISTEME_URL/search?q=QUERY&limit=5'for relevant laws (Conway, Amdahl, CAP, etc.) and patterns - Detect -- identify violations and structural smells via
curl -s '$EPISTEME_URL/graph/ID/neighbors' - Expand --
curl -s -X POST $EPISTEME_URL/graph/subgraph -H 'Content-Type: application/json' -d '{"entity_id":"LAW-xxx","depth":2}'to pull all entities and relationships within N hops for broader context - Audit --
curl -s '$EPISTEME_URL/graph/contradictions'to surface conflicting design principles in scope;curl -s '$EPISTEME_URL/graph/infer'to discover implied enforcement chains not yet explicit in the graph - Score -- risk-weighted compliance assessment
- Report -- findings with law citations and remediation paths
Output Format
# Architecture Analysis: [System/Decision]
## Compliance Score: [X/10]
## Law Violations
| Law | Violation | Severity | Remediation |
|-----|-----------|----------|-------------|
| [LAW-xxx] [Name] | [how violated] | [low/med/high] | [DP-xxx or RF-xxx] |
## Structural Risks
- [Risk description] -> [evidence from graph]
## Recommendations
1. [Concrete change] -- grounded in [entity ID]
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.
- 10d ago First seen · 51 lines · 51 tokens per session scan B 0454d7c1b150
architecture-analyst is a skill published in the GitHub repository epicsagas/Episteme (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 51 tokens to every session and 601 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
understand-figma
Analyze a Figma file via the Figma REST API and generate an interactive design knowledge graph (pages, screens, components, component sets, instances, design tokens) with a kind:"design" dashboard.
b123d-modeling
Use this skill when asked to model, build, or modify a 3D part or assembly with build123d — from a text description, a technical drawing (image or PDF), dimensions in a spec, or an existing STEP/STL file.
umg-mcp-authoring
Use when Codex needs to create, edit, inspect, validate, or demo UE5.8 UMG interfaces through Unreal Motion Graphics MCP/FabUmgMcp, especially target/default workflows, widget tree authoring, HLSL-backed UI materials, Sequencer widget animations, Blueprint event wiring, readback validation, or operation-trace demo…
memoire-design-tooling
Use when a task spans interface understanding, design-system memory, UI audits, design CI, Figma, shadcn or Tailwind code generation, research, or agent design workflows and needs the correct Memi capability selected.
build-swiftui-interface
Use when a coding agent must design, scaffold, implement, or verify an iOS or macOS SwiftUI interface with Apple-platform state, accessibility, availability, testing, and Xcode evidence.
shadcn-sveltekit-design
Use when building, redesigning, beautifying, or refactoring SvelteKit pages and reusable components with shadcn-svelte, Bits UI, or the shadcn-svelte MCP. Trigger on landing pages, dashboards, marketing sites, app shells, forms, navbars, tables, dialogs, responsive layouts, theming, icon selection, and requests to…