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 mattmre/EVOKORE-MCP-PUBLIC --skill agent-archetypesgit clone --depth 1 https://github.com/mattmre/EVOKORE-MCP-PUBLICWrote 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/mattmre/evokore-mcp-public/agent-archetypes)<a href="https://agentmods.dev/skills/mattmre/evokore-mcp-public/agent-archetypes"><img src="https://agentmods.dev/badge/skills/mattmre/evokore-mcp-public/agent-archetypes/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/mattmre/evokore-mcp-public/agent-archetypes"><img src="https://agentmods.dev/badge/skills/mattmre/evokore-mcp-public/agent-archetypes.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 | $0.00016 | $0.02735 |
| Opus 5 | $0.00008 | $0.01367 |
| Sonnet 5 | $0.00003 | $0.00547 |
| Haiku 4.5 | $0.00002 | $0.00274 |
Grade A, and why
agent-archetypes 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 8d 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 — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Archetypes
Reference architecture for multi-agent orchestration systems. These six agent definitions, imported from Agent33, establish the core roles, governance boundaries, and capability assignments needed to run a structured agent pipeline.
Each agent is defined as a JSON file that declares its role, inputs/outputs, governance scope, capability set, and operational constraints. Together they form a composable team where the orchestrator decomposes work, the director plans strategy, workers execute, QA validates, the researcher gathers information, and the browser agent handles web interaction.
Agent Summary
| Agent | ID | Role | Scope | Key Capabilities | Escalation Target |
|---|---|---|---|---|---|
| Orchestrator | AGT-001 | orchestrator | full-system | P-01, P-02, P-03, P-05, V-05 | human-operator |
| Director | AGT-002 | director | project-level | P-01, P-02, P-03, P-04, P-05 | orchestrator |
| Code Worker | AGT-003 | worker | assigned-workspace | I-01, I-02, I-03, I-04, I-05 | orchestrator |
| QA | AGT-004 | qa | test-workspace | V-01, V-02, V-03 | orchestrator |
| Researcher | AGT-006 | researcher | read-only | X-01, X-02, X-03, X-04, X-05 | orchestrator |
| Browser Agent | -- | worker | browser-sandbox | (none assigned) | orchestrator |
Agent Traits and Constraints
- Orchestrator -- No dependencies; top of the chain. Has full-system command access and internal-only network. No parallel execution. 8192 token limit, 300s timeout, 3 retries.
- Director -- Reports to orchestrator. No direct command execution; plans only. Requires approval for scope changes. 8192 token limit, 240s timeout, 2 retries.
- Code Worker -- Reports to orchestrator. Scoped to assigned workspace with build/test/lint commands. Requires approval for deploy. Parallel execution allowed. 16384 token limit, 180s timeout.
- QA -- Reports to orchestrator. Scoped to test workspace with test/lint/check commands. Parallel execution allowed. 8192 token limit, 180s timeout.
- Researcher -- Optionally reports to orchestrator. Read-only scope with external-read network access. No parallel execution. 32768 token limit, 300s timeout.
- Browser Agent -- Optionally reports to orchestrator. Sandboxed browser scope with external-read network. Parallel execution allowed. 16384 token limit, 300s timeout.
What ships with it
15 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.
- AGT-013-loop-operator.json 3.5 KB
- AGT-014-security-sentinel.json 3.2 KB
- AGT-015-performance-engineer.json 2.6 KB
- AGT-016-memory-steward.json 2.6 KB
- AGT-017-quality-engineer.json 2.9 KB
- AGT-018-governance-gate.json 2.6 KB
- AGT-019-claims-coordinator.json 3.1 KB
- AGT-020-neural-optimizer.json 2.9 KB
- AGT-021-release-engineer.json 3.1 KB
- browser-agent.json 1.9 KB
- director.json 1.8 KB
- orchestrator.json 1.6 KB
- qa.json 1.7 KB
- researcher.json 1.8 KB
- worker.json 1.9 KB
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.
- 8d ago First seen · 218 lines · 16 tokens per session scan A d927897f99da
agent-archetypes is a skill published in the GitHub repository mattmre/EVOKORE-MCP-PUBLIC (3 stars, last pushed 3mo ago), licensed MIT. It adds 16 tokens to every session and 2,735 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
law-of-similarity
Apply the Law of Similarity — shared colour, shape, or size signals that elements belong to one category. Use when signalling relationships across distance. For grouping by position, use law-of-proximity.
law-of-common-region
Apply the Law of Common Region — a shared container, background, or border groups elements regardless of spacing. Use when grouping must survive a tight layout. For grouping by spacing alone, use law-of-proximity.
critique-visual-hierarchy
Critique a rendered screen's hierarchy — entry point, eye flow, weight distribution, and emphasis. Use when attention lands in the wrong place. For establishing hierarchy in new work, use visual-hierarchy (ui-design).
version-control-strategy
Define version control for design files, components, and libraries — branching, naming, and release. Use when file history is chaotic. For design system contribution rules, use design-system-governance (design-systems).
presentation-deck
Structure a design presentation for a specific audience and decision. Use when presenting internally. For a portfolio narrative use case-study; for the written argument use design-rationale.
accessibility-test-plan
Plan accessibility testing — assistive technologies, participant criteria, WCAG coverage, and session protocol. Use when scheduling testing with real AT users. Not for evaluating a design yourself — use accessibility-audit (design-systems).