Team Agent Orchestration
affaan-m/ECC
Run team-based orchestration for agent squads: work items with owners and scope, agent Kanban state, branch isolation, control pane visibility, and merge gates.
A portable orchestrator that completes a high-level task through 5 stages — clarify → context-gather → plan → implement → verify.
MITAuto-check passed
Install Harness Starter
$ npx skills add greatSumini/cc-system --skill harness-starter -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install greatSumini/cc-system harness-starter --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/greatSumini/cc-system.git skills-src && mkdir -p .claude/skills && cp -r skills-src/harness-starter .claude/skills/harness-starter && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "harness-starter" agent skill from https://github.com/greatSumini/cc-system/tree/main/harness-starter into .claude/skills/harness-starter/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-starter", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/greatSumini/cc-system/tree/main/harness-starterType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add greatSumini/cc-system --skill harness-starter -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install greatSumini/cc-system harness-starter --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/greatSumini/cc-system.git skills-src && mkdir -p .agents/skills && cp -r skills-src/harness-starter .agents/skills/harness-starter && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "harness-starter" agent skill from https://github.com/greatSumini/cc-system/tree/main/harness-starter into .agents/skills/harness-starter/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-starter", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add greatSumini/cc-system --skill harness-starter -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install greatSumini/cc-system harness-starter --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/greatSumini/cc-system.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/harness-starter .cursor/skills/harness-starter && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "harness-starter" agent skill from https://github.com/greatSumini/cc-system/tree/main/harness-starter into .cursor/skills/harness-starter/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-starter", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/greatSumini/cc-system.git --path harness-starter--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add greatSumini/cc-system --skill harness-starter -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install greatSumini/cc-system harness-starter --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/greatSumini/cc-system.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/harness-starter .gemini/skills/harness-starter && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "harness-starter" agent skill from https://github.com/greatSumini/cc-system/tree/main/harness-starter into .gemini/skills/harness-starter/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-starter", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install greatSumini/cc-system harness-starterInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add greatSumini/cc-system --skill harness-starter -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/greatSumini/cc-system.git skills-src && mkdir -p .github/skills && cp -r skills-src/harness-starter .github/skills/harness-starter && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "harness-starter" agent skill from https://github.com/greatSumini/cc-system/tree/main/harness-starter into .github/skills/harness-starter/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-starter", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add greatSumini/cc-system --skill harness-starter -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install greatSumini/cc-system harness-starter --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/greatSumini/cc-system.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/harness-starter .opencode/skills/harness-starter && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "harness-starter" agent skill from https://github.com/greatSumini/cc-system/tree/main/harness-starter into .opencode/skills/harness-starter/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-starter", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
harness-starter- GitHub stars
- 438
- Token cost
- ~1.3k tokens
- SKILL.md length
- 584 words
- Files
- 11 (incl. references)
- Skills in repo
- 12
- Repo updated
- First seen
- Licence
- MIT
At a glance
A portable orchestrator that completes a high-level task through 5 stages — clarify → context-gather → plan → implement → verify.
- SKILL.md covers 0. Setup, Stage procedure (judge skip…, Principles and Partial use (cherry-pick)
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Harness Starter is an agent skill from greatSumini/cc-system. A portable orchestrator that completes a high-level task through 5 stages — clarify → context-gather → plan → implement → verify. Each stage hands off via file artifacts, and a stage is skipped when its artifact already exists. The plan is decomposed into a task graph (DAG); independent nodes run in parallel, dependent nodes run in order.
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 13 other files, including reference files (for example `README.md`, `agents/clarify.md` and `agents/context-gather.md`).
The licence is MIT.
Example prompts
- “/harness-starter”
What it can do on your machine
Read from SKILL.md and the folder at commit 172bdd4. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Harness Starter loads about 1.3k tokens when it runs, and up to ~4.1k if it reads all its reference files. Until then it costs about 89 tokens; SKILL.md has 584 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from greatSumini/cc-system at commit 172bdd4, republished under its MIT licence (© greatSumini). 584 words, ~1,295 tokens.
Download SKILL.mdSave it as
.claude/skills/harness-starter/SKILL.md (or your agent's skills folder). This skill also uses 10 other files; get the full folder from GitHub.- name
- harness-starter
- description
- A portable orchestrator that completes a high-level task through 5 stages — clarify → context-gather → plan → implement → verify. Each stage hands off via file artifacts, and a stage is skipped when its artifact already exists. The plan is decomposed into a task graph (DAG); independent nodes run in parallel, dependent nodes run in order.
$ARGUMENTS
Handle the request above through the 5-stage harness. You are the orchestrator. Do not analyze or implement code yourself — delegate each stage to a dedicated subagent, hand off via artifacts, and schedule the task graph.
First, study references/artifacts.md (artifact contracts) and references/decomposition.md (decomposition criteria).
If references/conventions.md is filled in, pass its contents into every delegation prompt.
0. Setup
- Choose a
<slug>(kebab-case) to identify the task. - Create
.harness/{specs,context,plans,reports}/if missing.
Stage procedure (judge skip before each stage)
Each stage is skipped when its artifact already exists (reuse outputs made by external tools or humans).
1. Clarify
- If
.harness/specs/<slug>.spec.mdexists → skip. - Otherwise delegate to the
harness-clarifyagent → producesspec.md. - If ambiguity is high, clarify may ask the user (questions are allowed in this stage only).
2. Context Gather
- If
.harness/context/<slug>.context.mdexists → skip. - Otherwise give the spec to
harness-contextand delegate → producescontext.md. (read-only)
3. Plan
- If
.harness/plans/<slug>.plan.mdexists → skip (treat as a validated plan). - Otherwise give spec + context to
harness-plannerand delegate → producesplan.md(task graph). - Check the returned plan against the decomposition checklist (decomposition.md): 3–6 nodes? per-node acceptanceCriteria? are parallel nodes file/module-scoped (no conflicts)? no cycles in blockedBy? If anything is off, ask the planner to fix it (up to 2 times).
- If human approval is desired, summarize the plan and confirm before proceeding (optional).
4. Implement — wavefront execution of the task graph
Execute plan.md nodes in parallel, wave by wave. No locks or scripts — the orchestrator schedules:
loop:
1. ready = nodes whose blockedBy are all status=done AND whose own status=pending
2. if ready is empty but unfinished nodes remain → deadlock (cycle/stuck). Stop and report.
3. delegate the ready nodes in parallel within a single message:
for each node, Task(harness-implementer, input = that node + spec + context + conventions)
(nodes in the same wave are file/module-scoped, so there are no write conflicts — safe to parallelize)
4. on each node completion, update its status in plan.md to done (or failed).
5. when all nodes are done, finish.- Within one wave, issue multiple implementer Tasks in the same message (do not wait for one to finish).
- If a node fails: do not advance its dependents; re-delegate the failed node once (attach a cause summary). If it still fails, stop and report.
- Scope escalation: if an implementer reports it needs to edit a shared/crosscutting file outside its scope
(it must NOT have edited it), add a new wire-up node scoped to that file,
blockedBythe nodes that feed it, and schedule it in a later wave. This converts a would-be parallel collision into a serialized node. - When in doubt, serialize. Parallelism is an optimization, not a requirement. If you can't be confident two ready nodes are truly independent (disjoint files, no semantic dependency), run them in separate waves instead. A single-file or uncertain plan should just run sequentially — correctness over speed.
Show full SKILL.md (203 more words)Show less
5. Verify
- When all nodes are done, delegate to
harness-verifier→ producesreport.md. Input = spec (acceptance criteria) + plan (nodes) + actual changes. - If verdict=PASS, report completion.
- If verdict=FAIL: per the report's "on failure" instruction, reset only the failed nodes to status=pending and run one more wavefront pass (fix loop). If still FAIL, stop and report to the human.
Principles
- Stages hand off only via artifacts. Do not let the next-stage agent rely on "context in your head" — always have it read the files (subagents start with fresh context).
- The orchestrator does not implement. Analysis/exploration/implementation/verification are all done by subagents. You only schedule, manage artifacts, and judge skips.
- Do not manufacture over-verification or over-decomposition. A trivial task may have a 1-node plan and a light verify. Scale to the size.
- User questions only in the clarify stage. Later stages proceed on the assumptions recorded in the artifacts.
- For a single-node task, the wavefront is just one implementer call — create no overhead.
Partial use (cherry-pick)
You need not run the whole harness. Since each stage's artifact is a contract:
- Use this harness only up to plan, then implement/verify with another tool → hand over
plan.md. - Drop an externally produced
spec.md/plan.mdinto.harness/and that stage is skipped automatically.
© greatSumini, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 10 other files (references) in harness-starter of greatSumini/cc-system.
- SKILL.md
- README.md
- agents/clarify.md
- agents/context-gather.md
- agents/implementer.md
- agents/planner.md
- agents/verifier.md
- prompt/install-harness-starter.md
- references/artifacts.md
- references/conventions.md
- references/decomposition.md
Open the folder on GitHubat commit 172bdd4
Compare with similar skills
Harness Starter next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Harness Starter this skillgreatSumini/cc-system | 438 | — | ~1.3k | Automated safety check: Pass | MIT | |
| Team Agent Orchestrationaffaan-m/ECC | 276k | 1 repos | ~1.2k | Automated safety check: Pass | MIT | |
| Orca Orchestrationstablyai/orca | 88k | — | ~916 | Automated safety check: Pass | MIT | |
| Agent Orchestrator Taskruvnet/ruflo | 74k | 2 repos | ~1k | Automated safety check: Pass | MIT | |
| Plan Orchestrateaffaan-m/ECC | 276k | 1 repos | ~4.5k | Automated safety check: Pass | MIT | |
| Orchestratesickn33/agentic-awesome-skills | 47k | 1 repos | ~692 | Automated safety check: Pass | MIT |
Similar skills
Orca Orchestration
stablyai/orca
Coordinate supervised Orca workers: threaded messages, blocking ask/reply, task dispatch, worker_done/escalation waits, task DAGs, decision gates, coordinator…
Agent Orchestrator Task
ruvnet/ruflo
Agent skill for orchestrator-task - invoke with $agent-orchestrator-task
Plan Orchestrate
affaan-m/ECC
Read a plan document, decompose it into steps, design a per-step agent chain from the ECC catalogue, and emit ready-to-paste /orchestrate custom prompts.
Orchestrate
sickn33/agentic-awesome-skills
Coordinate focused subagents on substantial work, keep their ownership non-overlapping, and integrate verified results.
Swarm Orchestration
ruvnet/ruflo
Coordinates a hierarchical swarm of specialized agents through the claude-flow CLI for work that spans several files or modules at once.
More from greatSumini/cc-system
All 12 skills in this repoSlash Command Creator
greatSumini/cc-system
Guide for creating Claude Code slash commands. An agent skill from greatSumini/cc-system.
Subagent Creator
greatSumini/cc-system
Create specialized Claude Code sub-agents with custom system prompts and tool configurations.
Cc Usage Audit
greatSumini/cc-system
한 프로젝트에서 사용자가 Claude Code에 입력한 프롬프트·작업 이력을 분석해 (1) 사용 패턴 정량화, (2) 사용자의 개발 철학 추출(근거 인용), (3) 그 철학을 렌즈로 한 메타 시스템(하니스·게이트·CI·프로세스) audit, (4) 우선순위가 매겨진 개선점 발굴을 수행한다.
Hook Creator
greatSumini/cc-system
Create and configure Claude Code hooks for customizing agent behavior.
Youtube Collector
greatSumini/cc-system
유튜브 채널을 등록하고 새 컨텐츠를 수집하여 자막 기반 요약을 생성하는 skill. An agent skill from greatSumini/cc-system.
Ship
greatSumini/cc-system
지금까지의 작업을 한 번에 출하한다 — 커밋 → push → PR 생성 → squash merge. An agent skill from greatSumini/cc-system.
Questions about Harness Starter
What does Harness Starter do?
A portable orchestrator that completes a high-level task through 5 stages — clarify → context-gather → plan → implement → verify. Harness Starter is an agent skill from greatSumini/cc-system. A portable orchestrator that completes a high-level task through 5 stages — clarify → context-gather → plan → implement → verify.
How do I install Harness Starter in Claude Code?
Run `npx skills add greatSumini/cc-system --skill harness-starter -a claude-code`. Or copy the skill folder (harness-starter in greatSumini/cc-system) into .claude/skills/harness-starter in your project. Claude Code loads it when a task matches its description.
How do I install Harness Starter in Codex?
Run `npx skills add greatSumini/cc-system --skill harness-starter -a codex`. Or copy the skill folder (harness-starter in greatSumini/cc-system) into .agents/skills/harness-starter in your project. Codex loads it when a task matches its description.
Can I use Harness Starter in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add greatSumini/cc-system --skill harness-starter -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/harness-starter, .gemini/skills/harness-starter, .github/skills/harness-starter and .opencode/skills/harness-starter in your project.
What does Harness Starter need to run?
SKILL.md names no scripts, command-line tools or credentials: Harness Starter is instructions for the agent only.
Does Harness Starter access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Harness Starter safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Harness Starter use?
Harness Starter is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Harness Starter use?
About 1.3k tokens (SKILL.md is roughly 5.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.8k tokens, read only when the agent opens those files.
What are the alternatives to Harness Starter?
Skills that share tags, products or a category with Harness Starter: Team Agent Orchestration (affaan-m/ECC, 276k stars), Orca Orchestration (stablyai/orca, 88k stars), Agent Orchestrator Task (ruvnet/ruflo, 74k stars) and Plan Orchestrate (affaan-m/ECC, 276k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Harness Starter?
greatSumini (a GitHub user) maintains it in greatSumini/cc-system, which has 438 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on June 9, 2026.
Source: greatSumini/cc-system on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.