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 vasuag09/harness-claude --skill orchestrategit clone --depth 1 https://github.com/vasuag09/harness-claudeWrote 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/vasuag09/harness-claude/orchestrate)<a href="https://agentmods.dev/skills/vasuag09/harness-claude/orchestrate"><img src="https://agentmods.dev/badge/skills/vasuag09/harness-claude/orchestrate.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 | $0.00140 | $0.02123 |
| Opus 5 | $0.00070 | $0.01061 |
| Sonnet 5 | $0.00028 | $0.00425 |
| Haiku 4.5 | $0.00014 | $0.00212 |
Grade A, and why
orchestrate 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 8d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/orchestrate — split the work, fan out, reconcile
Goal: take a task that spans many independent files and do it in parallel without two
workers ever clobbering the same file. This skill is the discipline layer: the platform
Workflow tool is the engine (parallel()/pipeline() + agent(prompt, {schema})); /harness-claude:orchestrate
is the lead — it decomposes the task, assigns one writer per file, dispatches workers
under explicit contracts, and reconciles their structured summaries into one result.
Opt-in. No default-pipeline skill or hook fans out. Parallel orchestration is always explicit. Git boundary: a run never commits or pushes unless you explicitly arm it in the objective; the lead creates one shared convention-named branch for the whole task before fan-out (
rules/git.md) — workers never branch. Token discipline: workers return summaries, not raw dumps (perrules/agents.md).
This is the parallel-fan-out mode from rules/agents.md. Reach for it when the work is
splittable into 3+ tasks whose concurrent members have disjoint write-sets. Tasks
that depend on each other's output aren't excluded — they run in later waves, not the
same batch. Only if the whole task is one unsplittable sequence is this the wrong mode.
How it works
decompose → group into waves (by depends_on) → per wave: verify disjointness → fan out (Workflow) → reconcile
- Decompose the task into subtasks (
T1,T2, …), each scoped to a set of files it will write and adepends_onlist of prior task IDs. (APLAN.mdfrom/harness-claude:planalready carries this format — seedocs/state-and-artifacts.md.) - Assign owners — every writable file belongs to exactly one subtask.
- Group into waves — topologically sort by
depends_on: tasks withdepends_on: []form wave 1; a task joins the wave after the latest wave of its dependencies. Waves run sequentially; tasks within a wave run in parallel. A fully-independent task set collapses to a single wave (identical to the pre-wave behavior — backward compatible). A dependency cycle is an error: refuse to run and name the cycle. - Per wave: verify disjointness, then fan out — before each wave's batch, check that its tasks' write-sets are pairwise disjoint (refuse and name the file if not); dispatch that wave via the Workflow tool; await it before starting the next wave.
- Reconcile the workers' structured summaries into one result; surface conflicts/failures.
What ships with it
1 file 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.
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.
- 8d ago First seen · 118 lines · 140 tokens per session scan A 25e293f40839
orchestrate is a skill published in the GitHub repository vasuag09/harness-claude (2 stars, last pushed 2mo ago), licensed MIT. It adds 140 tokens to every session and 2,123 once invoked, about $0.0007 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
pr-triage
4-phase PR backlog management with audit, deep code review, validated comments, and optional worktree setup. Use when triaging pull requests, catching up on pending code reviews, or managing a backlog of open PRs. Args: 'all' to review all, PR numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit…
audit-agents-skills
Audit Claude Code agents, skills, and commands for quality and production readiness. Use when evaluating skill quality, checking production readiness scores, or comparing agents against best-practice templates.
eval-agents
Audit Claude Code agents defined in .claude/agents/ for description specificity, model tier appropriateness, tools scoping, and system prompt quality. Detects dispatch ambiguity between agents, flags over-permissive tool grants, and checks for human-in-the-loop patterns that break programmatic orchestration. Use when…
check-cache-bugs
Audit Claude Code setup for cache bugs (CC#40524): sentinel, --resume/--continue, attribution header + ArkNill B3/B4/B5.
issue-triage
3-phase issue backlog management with audit, deep analysis, and validated triage actions. Use when triaging GitHub issues, sorting bug reports, cleaning up stale tickets, or detecting duplicate issues. Args: 'all' to analyze all, issue numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit only.
git-ai-archaeology
Analyze AI config evolution in a git repo. Use when mapping AI adoption history, finding when configs were first introduced, charting commit velocity by month, or identifying maturity phases in a project's AI tooling.