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 burin-labs/harn --skill harn-orchestrationgit clone --depth 1 https://github.com/burin-labs/harnWrote 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/burin-labs/harn/harn-orchestration)<a href="https://agentmods.dev/skills/burin-labs/harn/harn-orchestration"><img src="https://agentmods.dev/badge/skills/burin-labs/harn/harn-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/burin-labs/harn/harn-orchestration"><img src="https://agentmods.dev/badge/skills/burin-labs/harn/harn-orchestration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00020 | $0.01241 |
| Opus 5 | $0.00010 | $0.00620 |
| Sonnet 5 | $0.00004 | $0.00248 |
| Haiku 4.5 | $0.00002 | $0.00124 |
Grade A, and why
harn-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 11d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Harn orchestration
Use this skill for workflows, triggers, workers, handoffs, parallelism, durable
execution, and agent_loop composition.
Pair it with [[harn-agent]] for loop behavior, [[harn-testing]] for deterministic verification, and [[harn-product-quality]] for product projections.
One execution substrate
- Harn owns scheduling, lifecycle, transcript, replay, lineage, and audit.
- A host adapts Harn state into native UI and concrete capabilities.
- Harn Cloud durably runs the same semantics; it does not fork them.
- CLI, TUI, IDE, headless, and cloud should consume one execution contract.
- Do not add a second scheduler, retry engine, or completion model to a host.
- Repair drift at the owner or projection interface.
- Keep provider-specific behavior behind provider adapters.
Workflow design
- Model a workflow around a durable outcome and typed stages.
- Give every stage explicit input, output, failure, and compensation behavior.
- Keep the external interface small; hide composition inside a deep module.
- Use existing stdlib primitives before adding runtime mechanics.
- Keep pure decisions separate from host effects.
- Route effects through
harness.*. - Make idempotency and resume semantics explicit.
- Persist checkpoints before expensive or irreversible stages.
Agent loops
- Use
agent_loopas the one agent entry point; useharness.llm.callorharness.llm.completionfor one model request and leave interactive input and editor state to the host. - Build the flat
AgentSpecwithagent_optionsoragent_preset; accept its six named component records when a boundary needs only part of the contract. - Bound iterations, tool duration, concurrency, tokens, and cost.
- Prefer structural progress and lifecycle events over prompt conventions.
- Define completion against observable artifacts or receipts.
- Use deterministic gates before model judges.
- Put resilience in a composable
llm_caller. - Keep a stable session id for durable work.
- Use
harness.agentfor open, snapshot, fork, compact, inject, and lifecycle operations. Do not add a parallel ambient session API. - Treat stop, wait, stand-down, and pivot as lifecycle events.
- Return
AgentResultand project its producer-ownedterminal.kind; hosts do not derive lifecycle state from text or transport stop reasons.
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.
- 11d ago First seen · 137 lines · 20 tokens per session scan A 24ee2f1c5d29
harn-orchestration is a skill published in the GitHub repository burin-labs/harn (22 stars, last pushed today), licensed Apache-2.0. It adds 20 tokens to every session and 1,241 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 2026-08-30.
Other skills, from other repositories
translate
A translation tool for converting user-provided text between languages, with Chinese and English as the default pair.
agent-communication-protocol
Open protocol for AI agent interoperability enabling standardized communication between agents, applications, and humans across different frameworks.
self-host-studio
Install and self-host deco Studio (the open-source control plane) on the user's own infrastructure. Use when the user wants to install, run, self-host, or deploy Studio locally (Docker, Rancher Desktop, kind, minikube) or on Kubernetes (managed or self-managed), or asks to "install Studio", "self-host decocms"…
gh-issue
Fetch a GitHub issue, create a branch, implement with TDD, and open a PR.
gh-issues
Walk over all open GitHub issues that are unassigned or assigned to the current user, and process each one via the /gh-issue skill, sequentially.
module-new
Scaffold a new Gacela module under src/php/ with Facade, Provider, and CLAUDE.md.