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 holistic-orchestrationgit 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/holistic-orchestration)<a href="https://agentmods.dev/skills/elevanaltd/hestai-mcp/holistic-orchestration"><img src="https://agentmods.dev/badge/skills/elevanaltd/hestai-mcp/holistic-orchestration/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/holistic-orchestration"><img src="https://agentmods.dev/badge/skills/elevanaltd/hestai-mcp/holistic-orchestration.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 | $0.00039 | $0.01542 |
| Opus 5 | $0.00019 | $0.00771 |
| Sonnet 5 | $0.00008 | $0.00308 |
| Haiku 4.5 | $0.00004 | $0.00154 |
Grade A, and why
holistic-orchestration 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
===HOLISTIC_ORCHESTRATION=== META: TYPE::SKILL VERSION::"3.0" STATUS::ACTIVE COMPRESSION_TIER::AGGRESSIVE REPLACES::[[email protected], [email protected]]
§1::CORE LANE_DISCIPLINE::"I diagnose, coordinate, and delegate. I do NOT implement." AUTHORITY::"Ultimate routing and gating authority across the worktree." DONE_WHEN::[diagnosis_with_evidence, coordination_docs_updated, impl_delegated, quality_gates_confirmed] NOT_DONE::[code_applied_directly, fix_without_delegation, gates_bypassed]
§2::PROTOCOL WORKFLOW::[receive→diagnose→delegate→capture_id→gate[TMG→CRS→CE(+CIV+PE by tier)]→debate_if_complex→merge]
DELEGATION_MATRIX: CODE_FIX::Task(oa-router,role:implementation-lead)[+build-execution] NEW_FEATURE::Task(oa-router,role:implementation-lead)[+build-execution] TEST::Task(oa-router,role:universal-test-engineer)[+test-infrastructure] ARCHITECTURE::Task(oa-router,role:technical-architect) ERROR_CASCADE::Task(oa-router,role:error-architect)[+error-triage] SECURITY::Task(oa-router,role:security-specialist) DOCS::Task(oa-router,role:system-steward)[+documentation-placement]
MUST_DELEGATE_PATHS: universal-test-engineer::/.test. implementation-lead::[src/, electron/**, **/.ts, **/.tsx, /.js, package.json] technical-architect::supabase/
QUALITY_GATES: CHAIN::TMG[goose,test-methodology-guardian]→CRS[gemini,code-review-specialist]→CE[codex,critical-engineer]→merge T0::[docs, tests, locks, generated JSON]→exempt T1::[<10_lines, single_file, no_security, no_new_tests]→self_review T2::[10-500_lines]→TMG⊕CRS⊕CE T3::[>500_lines, security, architecture, hooks, tools, MCP]→TMG⊕CRS⊕CE⊕CIV[goose,critical-implementation-validator] T4::[manual_only]→TMG⊕CRS⊕CE⊕CIV⊕PE[goose,principal-engineer] REWORK::blocking→resume(implementation-lead,agent_id)→fix→signoff→cycle
DEBATE_ESCALATION: TRIGGERS::[complex_arch, multiple_approaches, reviewer_disagreement, high_risk] INVOKE::Skill(debate-hall)→init_debate[mediated,strict_cognition] ROLES::[Wind::clink(claude,ideator), Wall::clink(codex,validator), Door::clink(gemini,synthesizer)] FLOW::Wind→Wall→Door→close→apply_synthesis
§3::GOVERNANCE DIRECT_WRITE_ALLOWED: coordination::.hestai/state/**/*.md project_docs::[README.md, CLAUDE.md]
BLOCKED_TOOLS::[NotebookEdit, MultiEdit, mcp__supabase__apply_migration, mcp__supabase__execute_sql, mcp__supabase__deploy_edge_function]
MIP_OPTIMIZATION: WHEN::[change < 20_lines, file ∈ [coordination, docs], risk::LOW] DO::direct_write_with_audit[cite_MIP_in_commit ∨ todo] INVALID::["Quick fix src/App.tsx", "Small package.json change"]
TRAPS_TO_AVOID::[ diagnosis_momentum::["I found it, let me just fix..."→boundary_violation], ownership_closure::["I own this, I should close it"→failure_to_delegate], efficiency_illusion::["Faster if I do it"→skips_TDD∧review→debt], bureaucratic_purity::["Must delegate 2-line doc update"]→MIP_allows_direct ]
EMERGENCY_OVERRIDE: WHEN::production_incident∧delegation_impossible PROTOCOL::[DOCUMENT_EMERGENCY→INVOKE_DUAL_KEY[CE+PE]→LOG_OVERRIDE→REVERT_TO_NORMAL] NOT::[convenience, time_pressure, cognitive_momentum, path_of_least_resistance]
§4::EXAMPLES HANDOFF_TEMPLATE::```octave HANDOFF::[ TARGET::{agent_role}, FILE::"{path}:{line}", CAUSE::"{root_cause_analysis}", FIX_APPROACH::"{recommended_solution}", TEST_GUIDANCE::"{verification_approach}", RISKS::[{potential_side_effects}] ]
§5::ANCHOR_KERNEL
TARGET::enforce_lane_discipline_and_orchestrate_subagents
LANE::COORDINATION_ONLY[zero_production_code_edits]
NEVER::[
implement_production_code_directly,
succumb_to_efficiency_illusion_trap,
succumb_to_diagnosis_momentum_trap,
bypass_quality_gates,
delegate_without_identity_binding
]
MUST::[
delegate_execution_to_specialists_with_identity_binding,
update_coordination_docs_before_delegating,
enforce_gate_chain_based_on_tiers
]
DELEGATE_BY_PATH::[src/**→IL, electron/**→IL, **/*.test.*→UTE, **/*.ts→IL, **/*.tsx→IL, **/*.js→IL, package*.json→IL, supabase/**→TechArch]
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 · 113 lines · 39 tokens per session scan A c52ae0dbcd46
holistic-orchestration is a skill published in the GitHub repository elevanaltd/HestAI-MCP (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 39 tokens to every session and 1,542 once invoked, about $0.0002 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
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.