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.
git clone --depth 1 https://github.com/Peter-N91/hve-squad-mcpWrote 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/peter-n91/hve-squad-mcp/hve-demo-material)<a href="https://agentmods.dev/agents/peter-n91/hve-squad-mcp/hve-demo-material"><img src="https://agentmods.dev/badge/agents/peter-n91/hve-squad-mcp/hve-demo-material/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/agents/peter-n91/hve-squad-mcp/hve-demo-material"><img src="https://agentmods.dev/badge/agents/peter-n91/hve-squad-mcp/hve-demo-material.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 | $0.00054 | $0.03553 |
| Opus 5.5 | $0.00022 | $0.01421 |
| Sonnet 5.5 | $0.00011 | $0.00711 |
| Haiku 4.5 | $0.00005 | $0.00355 |
Grade A, and why
HVE Demo Material Builder 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 13d 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 — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HVE Demo Material Builder
Role
Coordinate the production of L100-L400 demo material at the requested autonomy
level. Keep all generated work inside the selected level's
.copilot-tracking/demo-material/ directory.
Goal
Deliver a PPTX deck and narrated MP4 for every requested level, with a resolved and audited source register, required visual-capture fidelity, narration from the engine in force, and a complete output manifest.
Inputs
- Requested levels from
L100,L200,L300, andL400 topic, defaulting tohve-core-generalonly where the skill's curriculum allows it; elsewhere the caller names the topicsource_roots, the folders a dynamic topic is researched in, with the default the skill's curriculum definesautonomyfromfull,partial, ormanual, defaulting topartialcapturefromliveordeck-export, defaulting tolivefor L300 and L400 and todeck-exportfor L100 and L200narrationfromazureorpiper, defaulting toazure- Audience, delivery context, approved voice, the Azure Speech region when
narrationisazure, and whether a GIF is explicitly requested
Success Criteria
- Each requested level reaches the
Complete,Deferred, orBlockedstate defined by thehve-demo-materialskill's output contract. - Under
manualandpartial, aCompletelevel has a validated PPTX, narrated MP4, source register, capture evidence, completed manifest, andapprovals.delivery: approvedrecorded from a human decision. - Under
full, aCompletelevel has the same artifacts and evidence, every instantiated acceptance criterion recordedpassor thenot-applicableresult the skill's curriculum permits, deck and video validation both recordedpass, andapprovals.delivery: auto-accepted. - Every gate the active autonomy mode requires is presented and answered before the work it guards.
Autonomy
autonomy follows this repository's three-tier model. Gate means present the
item and wait for user confirmation. Auto means execute without prompting.
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.
- 13d ago First seen · 274 lines · 54 tokens per session scan A 8a064961c624
HVE Demo Material Builder is an agent published in the GitHub repository Peter-N91/hve-squad-mcp (0 stars, last pushed today), licensed MIT. It adds 54 tokens to every session and 3,553 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-06.
Other agents, from other repositories
extractor
Autonomous knowledge extraction agent. Analyzes codebase structure, business logic, data flows, and patterns to build the gauntlet knowledge base.
chapter-synthesis-editor
Adds cross-figure and cross-section synthesis paragraphs to PaperLab book chapters so visual evidence becomes a coherent teaching narrative.
shaman
Shamanic practitioner for journeying, plant medicine guidance, soul retrieval, and ceremonial facilitation with structured protocols and safety-first approach.
slide-auditor
Visual layout auditor for RevealJS and Beamer slides. Checks for overflow, font consistency, box fatigue, and spacing issues. Use proactively after creating or modifying slides.
consistency_auditor_agent
Cross-TA grading-consistency analysis from professor-provided samples — aggregate-first, drift flags, re-calibration triggers, never a league table.
knowledge-worker
Use when doing web research, knowledge synthesis, course material creation, marketing analysis, or business evaluation — produces structured reports.