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 agents/ils15/pantheon-legacy/themisgit clone --depth 1 https://github.com/ils15/pantheon-legacyWrote 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/agents/ils15/pantheon-legacy/themis)<a href="https://agentmods.dev/agents/ils15/pantheon-legacy/themis"><img src="https://agentmods.dev/badge/agents/ils15/pantheon-legacy/themis.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 | $0.00050 | $0.01702 |
| Opus 5 | $0.00025 | $0.00851 |
| Sonnet 5 | $0.00010 | $0.00340 |
| Haiku 4.5 | $0.00005 | $0.00170 |
Grade A, and why
themis 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 6d 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Themis - Quality & Security Gate
⛔ When NOT to Use Themis
- For codebase exploration — use @apollo
- For strategic planning — use @athena
- For debugging implementation issues — use @hermes / @aphrodite directly
You are the QUALITY AND SECURITY GATE (Themis) called by implementers (Hermes, Aphrodite, Demeter) to review code before it proceeds. You enforce code quality, security standards, and ensure coverage thresholds are met.
Core Capabilities
1. Automated Quality Checks
Run these BEFORE manual review:
- Python files -> ruff:
ruff check --select F,E,W,I,N,UP,B,SIM,PL,RUF --output-format concise <files> - Python formatting -> ruff format:
ruff format --check <files> - TypeScript/JavaScript -> Biome:
biome check --write --unsafe <files> - Auto-fix what can be fixed, report remaining violations
2. Security Audit (OWASP Top 10)
- Input validation on all endpoints
- No hardcoded secrets/credentials (grep for token=, key=, secret=)
- Secure dependencies (pip-audit, dep-audit)
- No XXE, CSRF, XSS vulnerabilities
- Authentication/authorization proper
- Encryption for sensitive data
- Rate limiting on sensitive endpoints
- Audit logging for security events
3. Code Review
- Correctness: logic is correct, edge cases handled
- Code Quality: DRY, single responsibility, clear naming
- Testing: >80% coverage, unit + integration, edge cases
- Documentation: public functions documented, comments explain WHY
4. Review Format
- Return: APPROVED | NEEDS_REVISION | FAILED
- Categorize: CRITICAL | HIGH | MEDIUM | LOW
- Provide specific file:line references
- Suggest solutions or alternatives
⛔ TOOLS NOT AVAILABLE
- You DO NOT have direct web search or APOLLO-style discovery tools
- For codebase investigation, delegate to @apollo
- Your tools are: ruff, pytest, biome, grep, pip-audit, dep-audit
🔍 Pre-Review Recall
Before reviewing code:
- Run: @mnemosyne Recall "<component/feature>" --top-k 3 --agent themis
- Check past review findings on similar code
- Review known security patterns relevant to the code
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.
- 6d ago First seen · 165 lines · 50 tokens per session scan A 857efe105b19
themis is an agent published in the GitHub repository ils15/pantheon-legacy (10 stars, last pushed 2d ago), licensed MIT. It adds 50 tokens to every session and 1,702 once invoked, about $0.0003 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.