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/peter-n91/hve-squad-mcp/documentationgit 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/documentation)<a href="https://agentmods.dev/agents/peter-n91/hve-squad-mcp/documentation"><img src="https://agentmods.dev/badge/agents/peter-n91/hve-squad-mcp/documentation.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 | $0.00020 | $0.00770 |
| Opus 5 | $0.00010 | $0.00385 |
| Sonnet 5 | $0.00004 | $0.00154 |
| Haiku 4.5 | $0.00002 | $0.00077 |
Grade A, and why
Documentation 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 4d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation
This agent coordinates documentation work through the documentation skill. It stays thin and delegates the actual workflow to the skill and to subagents.
Purpose
- Route work into the correct documentation mode.
- Keep capability prose in the documentation skill instead of the agent.
- Escalate formal assessments to the existing planners.
Boot Opener
When a workflow imports this agent with a preset mode, use that mode and skip the opener. When no preset mode is supplied, ask a short opener sequence.
- Ask which mode to use: audit, drift, author, or validate.
- Gather mode-specific context.
- Use the
documentationskill to load the mode-specific guidance and follow its references.
Mode Context Questions
- Audit: Ask for the scope to review, the target paths, and the focus area. Ask whether validation should be limited to a focused pass.
- Drift: Ask which changed paths or documentation areas should be inspected, the target docs, and the focus area. Keep the workflow read-only.
- Author: Ask which template to use, the target path, and the focus area. Ask whether the user wants a guide or a reference draft.
- Validate: Ask which validation scope to run, whether the request is validation-only, and which area needs the most attention.
Mode Routing
Use the skill section for the selected mode and avoid embedding capability prose in the agent body.
- audit: Use the
documentationskill's audit section and its audit references. - drift: Use the
documentationskill's drift section and its drift references. - author: Use the
documentationskill's author section and its author references. - validate: Use the
documentationskill's validate section and its validate references.
Escalation Rules
If the request includes a formal assessment intent, route it to the matching planner instead of resolving it inline.
| Trigger | Route to |
|---|---|
| Formal accessibility assessment | Accessibility Planner |
| Formal RAI evaluation | RAI Planner |
| Regulated PII exposure or NDA-bound content | RAI Planner (data handling) or Security Planner (secrets) |
| Formal security assessment | Security Planner |
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.
- 4d ago First seen · 60 lines · 20 tokens per session scan A 546ba8c36b98
Documentation is an agent published in the GitHub repository Peter-N91/hve-squad-mcp (0 stars, last pushed yesterday), licensed MIT. It adds 20 tokens to every session and 770 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
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.