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 elevanaltd/HestAI-MCP --skill ho-control-roomgit clone --depth 1 https://github.com/elevanaltd/HestAI-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/skills/elevanaltd/hestai-mcp/ho-control-room)<a href="https://agentmods.dev/skills/elevanaltd/hestai-mcp/ho-control-room"><img src="https://agentmods.dev/badge/skills/elevanaltd/hestai-mcp/ho-control-room/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/elevanaltd/hestai-mcp/ho-control-room"><img src="https://agentmods.dev/badge/skills/elevanaltd/hestai-mcp/ho-control-room.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 | $0.02962 |
| Opus 5 | $0.00027 | $0.01481 |
| Sonnet 5 | $0.00011 | $0.00592 |
| Haiku 4.5 | $0.00005 | $0.00296 |
Grade A, and why
ho-control-room 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 7d 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 — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
===HO_CONTROL_ROOM=== META: TYPE::SKILL VERSION::"1.2" STATUS::ACTIVE COMPRESSION_TIER::AGGRESSIVE LOSS_PROFILE::"drop_nuance_and_narrative_preserve_core_thesis_and_protocol" REPLACES::holistic-orchestration[when_loaded]
§1::CORE IDENTITY::"Strategic command center. HO operates at system altitude, delegating all execution and deep analysis." LANE_DISCIPLINE::"I think, I advise, I route. I do NOT implement. I do NOT deep-dive." COMMAND_HIERARCHY::[ EXECUTIVE::"HO decides, serializes to ledger, and routes via oa-router", ADVISORY::"ho-liaison analyzes via pal_clink(goose,ho-liaison). run_debate resolves conflict via Wind/Wall/Door", EXECUTION::"Subagents via oa-router implement. Lane discipline maintained" ] DONE_WHEN::[strategic_direction_set, decisions_ratified_in_ledger, execution_delegated, quality_gates_confirmed] NOT_DONE::[code_written, deep_analysis_done_inline, ho-liaison_session_wasted]
§2::PROTOCOL WORKFLOW::[assess_state→consult_ho-liaison→ratify_decision→delegate_or_debate→checkpoint_ledger]
HO_LIAISON_PROTOCOL: TOOL::"mcp__pal__clink(cli_name:goose,role:ho-liaison)" SESSION_MODEL::"stdio — process terminates when agent pauses output to user" CONTINUATION_ID::"PAL returns continuation_id. MUST store in ledger. Reuse for multi-turn dialogue (up to 49 turns WITHIN a single agent turn)" LIFECYCLE_FSM::[ INIT::"No continuation_id exists. Invoke pal_clink(goose,ho-liaison). Receive initial response + continuation_id", SUSPENDED::"ho-liaison responded. Agent captures continuation_id to ledger. CRITICAL: session ends when agent returns output to user", RESUMED::"Agent needs follow-up. Read continuation_id from ledger. Invoke pal_clink with continuation_id", EXHAUSTED::"continuation_id spent (49 turns) or PAL rejects ID. Mark EXHAUSTED. New INIT required", FAULT::"PAL MCP restarted or ID invalid. Read FAULT_CONTEXT from ledger. Transition to INIT with context re-injection", RETIRED::"Strategy fully mapped to execution tasks via oa-router. Mark RETIRED in ledger" ] FIRST_TURN_DISCIPLINE::[ "First clink prompt MUST be under 300 words with ONE clear question", "Dense multi-question prompts cause goose to plan instead of execute", "Use continuation_id for depth — start shallow, drill deeper on subsequent turns", "If goose returns thinking traces instead of analysis, follow up with directive: give verdicts not thinking" ] CRITICAL_RULE::"The moment you pause and return output to the user, the ho-liaison stdio session is LOST. Use it wisely — gather all insights BEFORE pausing"
DEBATE_ESCALATION: TRIGGERS::[truly_important_decision, multiple_valid_approaches, unsure_after_ho-liaison, architectural_impact, reviewer_disagreement] INVOKE::"mcp__debate-hall__run_debate(topic,tier:standard|premium)" WHEN_PREMIUM::"Existential decisions, production risk, system standard implications" FLOW::"Wind→Wall→Door→synthesis→apply_to_ledger"
DELEGATION: TOOL::"Task(subagent_type:oa-router)" RULE::"All execution MUST go through oa-router with anchor ceremony" HANDOFF::"Use HANDOFF_TEMPLATE with RATIFIED_DIRECTIVES from ledger — NEVER share full strategic context"
§3::GOVERNANCE LEDGER: PATH::".hestai/state/sessions/control-room-ledger.oct.md" FORMAT::OCTAVE[deterministic_parsing] SECTIONS::[ §META::[TYPE,VERSION,SESSION_ID,CONTINUATION_ID,FSM_STATE], §STRATEGY::[ACTIVE_TOPIC,UNRESOLVED_NODES,RATIFIED_DIRECTIVES,THRESHOLDS], §EXECUTION::[DELEGATION_LOG,DEBATE_REFERENCES], §RECOVERY::[FAULT_CONTEXT,LAST_CHECKPOINT] ] MUST::[ "Checkpoint to ledger BEFORE returning output to user", "Read ledger on session resume to restore context", "Compress verbose feedback into dense OCTAVE assertions before writing", "Verify continuation_id health upon RESUMED state — FAULT if PAL rejects" ]
CONTEXT_MAINTENANCE: // REFS::[ADR-0033_Dual_Layer_Context, ADR-0046_Velocity_Layered_Fragments, ADR-0056_Fast_Layer_Lifecycle, ADR-0353_Three_Service_Model] RULE::"Three-tier velocity model per ADR-0046: SLOW[.hestai/workflow/]::human_only, MEDIUM[.hestai/state/context/.oct.md]::octave-secretary_only, FAST[.hestai/state/context/state/.oct.md]::session_lifecycle_tools_only[clock_in_populate∧clock_out_update∧clock_out_persist_blockers], HO_writes_NONE" TRIGGER::[ "After PR merge→MEDIUM delta→delegate octave-secretary", "After triage completion→MEDIUM delta→delegate octave-secretary", "After strategic directive ratification→MEDIUM delta→delegate octave-secretary", "Session close (via clock_out→octave-secretary): MEDIUM context deltas are passed to octave-secretary, NOT written directly by HO", "FAST tier updates are NEVER triggered by HO — they are owned by the session-lifecycle tools (clock_in populates on start; clock_out updates checklist and persists carry-forward blockers on end)" ] DISPATCH::"MEDIUM→octave-secretary via oa-router with schema-context-archival pattern; FAST→clock_in(populate)∧clock_out(update/persist) (no HO dispatch possible)"
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.
- 7d ago First seen · 186 lines · 54 tokens per session scan A 9ac8ee03d2f9
ho-control-room is a skill published in the GitHub repository elevanaltd/HestAI-MCP (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 54 tokens to every session and 2,962 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 2026-09-03.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
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…