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/epicsagas/episteme/code-reviewernpx skills add epicsagas/Episteme --skill code-reviewergit 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/code-reviewer)<a href="https://agentmods.dev/skills/epicsagas/episteme/code-reviewer"><img src="https://agentmods.dev/badge/skills/epicsagas/episteme/code-reviewer.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 | $0.00069 | $0.00799 |
| Opus 5 | $0.00034 | $0.00400 |
| Sonnet 5 | $0.00014 | $0.00160 |
| Haiku 4.5 | $0.00007 | $0.00080 |
Grade B, and why
code-reviewer 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 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.
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.
2. **Detect** -- `curl -s -X POST $EPISTEME_URL/analyze -H 'Content-Type: application/json' -d '{"code":"...","language":"python"}'` to identify smells automatically Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Then use `$EPISTEME_URL` and `-H "X-API-Key: $EPISTEME_API_KEY"` in all curl calls. How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You review code and PRs by detecting smells via the knowledge graph, ranking refactorings, and citing the engineering principles behind each finding.
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 code changes, PR description, or architectural proposal
- Detect --
curl -s -X POST $EPISTEME_URL/analyze -H 'Content-Type: application/json' -d '{"code":"...","language":"python"}'to identify smells automatically - Suggest --
curl -s -X POST $EPISTEME_URL/refactor -H 'Content-Type: application/json' -d '{"code":"...","language":"python","top_k":3}'for ranked fixes per detected smell - Map --
curl -s '$EPISTEME_URL/graph/ID?detail=full'andcurl -s '$EPISTEME_URL/graph/ID/neighbors'to connect smells to underlying principles - Report -- findings with entity citations, severity, and actionable fixes
Code analysis
Pass code directly in the JSON body — no temp file needed:
# Detect smells
curl -s -X POST $EPISTEME_URL/analyze \
-H 'Content-Type: application/json' \
-d '{"code":"class GodClass:\n def create(self): pass\n def delete(self): pass","language":"python"}'
# Get ranked refactorings
curl -s -X POST $EPISTEME_URL/refactor \
-H 'Content-Type: application/json' \
-d '{"code":"class GodClass:\n def create(self): pass\n def delete(self): pass","language":"python","top_k":3}'
Output Format
# Episteme Code Review
## Summary
[1-2 sentence overall assessment]
## Smell Detections
| Smell | Location | Severity | Related Principle |
|-------|----------|----------|-------------------|
| [Name] ([SMELL-xxx]) | [file:line] | [low/medium/high] | [LAW-xxx or DP-xxx] |
## Ranked Refactorings
1. **[Refactoring Name]** ([RF-xxx]) -- Priority: Critical
- Addresses: [SMELL-xxx]
- What to do: [concrete steps]
## Principle Violations
### [Entity Name] ([ID]) -- Violated
- **Violation**: [specific issue]
- **Fix**: [improvement via RF-xxx]
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 · 74 lines · 69 tokens per session scan B 6bec0f5301b8
code-reviewer is a skill published in the GitHub repository epicsagas/Episteme (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 69 tokens to every session and 799 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
memora
Use when working with persistent memory across sessions, storing/retrieving knowledge, managing TODOs/issues, or when context from previous sessions would be helpful.
brain-in-the-fish
Universal document evaluation engine — evaluate any document against any criteria using cognitively-modelled AI agents with ontology-grounded scoring.
prism
PRISM finds entities (genes, proteins, compounds) at the INTERSECTION of two or more property sets on RDF knowledge graphs via TogoMCP — e.g. "genes common to disease X and druggable pathway Y", "targets both linked to phenotype P and modulated by existing drugs". Use whenever the user asks a set-intersection /…
disease-analysis
Run a multi-scale disease pathophysiology analysis — molecular defects through to clinical symptoms — using TogoMCP (RDF Portal SPARQL), TogoID ID conversion, OLS4, and PubMed. Use whenever the user asks to "analyze a disease", build a disease mechanism model, find disease-associated proteins/pathways/drugs, map a…
research-article-analysis
Systematically validate a research article's claims against TogoMCP RDF databases — molecular formulas, reaction equations, pathways, protein function, GO definitions — instead of trusting the paper's text or keyword-search snippets. Use whenever the user asks to "analyze this paper/article", fact-check or validate a…
mcp-development
MCP Server Development Patterns and Best Practices.