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 skills/peter-n91/hve-squad/squadnpx skills add Peter-N91/hve-squad --skill squadgit clone --depth 1 https://github.com/Peter-N91/hve-squadWrote 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/peter-n91/hve-squad/squad)<a href="https://agentmods.dev/skills/peter-n91/hve-squad/squad"><img src="https://agentmods.dev/badge/skills/peter-n91/hve-squad/squad.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 | $0.00069 | $0.00910 |
| Opus 5 | $0.00034 | $0.00455 |
| Sonnet 5 | $0.00014 | $0.00182 |
| Haiku 4.5 | $0.00007 | $0.00091 |
Grade A, and why
squad 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Squad Operating Procedure
Overview
The squad is a user-invocable Squad Coordinator that dispatches a reusable cast of deployed HVE Core agents in parallel and persists roster, routing, decisions, and per-agent history under .copilot-tracking/squad/. There is no separate runtime: every squad verb is a thin convention over an existing HVE Core mechanism.
This skill packages the coordinator's operating procedure and the seed templates it stamps out on first run. The procedure lives in the reference files listed under Procedure below; the eleven companion instruction files that auto-apply when squad state is touched are catalogued in references/00-index.md.
Prerequisites
- A
runSubagentortasktool is available so the coordinator can dispatchuser-invocable: falseagents. - The deployed HVE Core cast exists (System Architecture Reviewer, Security Planner, RAI Planner, UX UI Designer, Finding Deep Verifier, PowerPoint Subagent) plus the squad-owned charters (Squad Scribe, Squad Researcher, Squad Lead, Squad Implementor, Squad Reviewer, Squad Challenger, Squad Technical Writer, Squad Prompt Engineer).
- Every roster Primary resolves to an installed agent that does not set
disable-model-invocation: true; the coordinator's Step 1b roster-resolution precheck confirms this before any dispatch. - The memory tool is available for durable per-agent notes under
/memories/repo/.
Procedure
The coordinator runs four stages each turn: init, route, decide, and handoff. Only the coordinator initiates state changes, and only the Squad Scribe performs the writes.
The procedure is split across the reference files below so that each agent loads only what its role needs. Read references/00-index.md first, then read the files your Skill Reference Contract names — not all of them.
| Reference | Covers |
|---|---|
| 00-index.md | Which file to read for which job, and the companion instruction files |
| profiles-and-packs.md | Squad profiles and add-on packs |
| operating-procedure.md | Init, Route, ledger reconciliation, Decide, Handoff, tool-to-mechanism mapping |
| gates-and-modes.md | Discovery, intake, council, implementation gates; autopilot and autonomy modes |
| federation.md | Federation layout, detection precedence, and federation modes |
| scribe-procedure.md | The Squad Scribe write procedure — Scribe only |
| entry-schemas.md | Recurring write shapes: decision and verdict entries, history, state.json |
| seed-templates.md | First-run state templates: team.md and routing.md |
| consumption.md | Consumption ledger templates and the cost estimator |
| federation-templates.md | Federation-root seed templates |
What ships with it
16 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.
- github-approval-watcher.workflow.yml 6.3 KB
- learnings/shared-learnings.md 2.8 KB
- mcp-server.template.json 3.6 KB
- mcp.template.json 6.0 KB
- references/00-index.md 5.1 KB
- references/consumption.md 14 KB
- references/entry-schemas.md 15 KB
- references/federation-templates.md 7.2 KB
- references/federation.md 17 KB
- references/gates-and-modes.md 19 KB
- references/operating-procedure.md 10 KB
- references/profiles-and-packs.md 8.2 KB
- references/scribe-procedure.md 41 KB
- references/seed-templates.md 22 KB
- squad-task.issue-template.yml 2.0 KB
- squad-watch.workflow.yml 24 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.
- 6d ago First seen · 50 lines · 69 tokens per session scan A ecb7d91566ec
squad is a skill published in the GitHub repository Peter-N91/hve-squad (11 stars, last pushed 2d ago), licensed MIT. It adds 69 tokens to every session and 910 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…