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 tool-governancegit 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/tool-governance)<a href="https://agentmods.dev/skills/mattmre/evokore-mcp-public/tool-governance"><img src="https://agentmods.dev/badge/skills/mattmre/evokore-mcp-public/tool-governance/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/tool-governance"><img src="https://agentmods.dev/badge/skills/mattmre/evokore-mcp-public/tool-governance.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 | $0.00020 | $0.00746 |
| Opus 5 | $0.00010 | $0.00373 |
| Sonnet 5 | $0.00004 | $0.00149 |
| Haiku 4.5 | $0.00002 | $0.00075 |
Grade A, and why
tool-governance 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tool Governance Skill
Overview
This skill imports Agent33's tool governance framework, providing a structured approach to managing tool access, approval, and runtime constraints. The framework is built on three core principles:
- Default-deny allowlisting -- Tools and network access are off unless explicitly approved via allowlist entries with scoped permissions.
- Provenance tracking -- Every tool must pass a provenance checklist covering ownership, licensing, security posture, and revocation plans.
- Progressive disclosure -- Tool schemas are loaded incrementally (L0 through L2+) so agents only consume the detail they need for the current task.
Reference Documents
| File | Purpose |
|---|---|
TOOL_GOVERNANCE.md |
Allowlist policy, provenance checklist, governance checkpoints |
TOOLS_AS_CODE.md |
Progressive disclosure levels, minimal schemas, registry workflow |
Tool Definitions
| Definition | Governance Constraints |
|---|---|
definitions/shell.yml |
Command allowlist/denylist, max timeout 120s, 1 MB output cap |
definitions/browser.yml |
Domain allowlist, max timeout 60s |
definitions/file_ops.yml |
Path allowlist, 1 MB output cap |
definitions/reader.yml |
Domain allowlist, 5 MB response cap |
definitions/search.yml |
Domain allowlist, configurable result count |
definitions/web_fetch.yml |
Domain allowlist, 5 MB response cap, max timeout 120s |
Progressive Disclosure Levels
| Level | What is loaded | When to use |
|---|---|---|
| L0 | Name + summary + owner | Tool discovery and inventory |
| L1 | Inputs/outputs summary | Task planning and tool selection |
| L2 | Full schema and constraints | Execution-time validation |
Integration with EVOKORE-MCP Security Layer
This governance framework complements EVOKORE-MCP's existing security mechanisms:
damage-control-rules.yaml-- EVOKORE's PreToolUse hook (scripts/damage-control.js) already enforces a deny-list of dangerous commands, zero-access paths for secrets, read-only paths, and no-delete paths. Agent33'sshell.ymldefinition provides the inverse view: an explicit allowlist of permitted executables. Together, the two layers form a defense-in-depth posture where EVOKORE blocks known-dangerous patterns and Agent33-style governance only permits known-safe commands.
What ships with it
8 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.
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 · 56 lines · 20 tokens per session scan A 29a4049a7045
tool-governance is a skill published in the GitHub repository mattmre/EVOKORE-MCP-PUBLIC (3 stars, last pushed 3mo ago), licensed MIT. It adds 20 tokens to every session and 746 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).