multi-agent

A full workflow for delivering a large software feature or epic, where specialized agents handle analysis, planning, design, coding, testing, review, operations, and release decisions.

In plain words
What is it for?
Use it to build a feature from scratch through tested implementation, security and stress checks, a final readiness verdict, operational artifacts, progress records, and a pull request.
Why use it?
It coordinates the stages and quality checks required for a large change instead of leaving planning, implementation, and delivery as separate manual tasks.

Skill for Claude CodeCodex

Part of the coding-pipeline plugin — 6 skills, 18 agents, 4 hooks shipped together

Install

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.

agentmods
npx agentmods add skills/luisfelipemoro/harness-devkit/multi-agent
Any agent
npx skills add LuisFelipeMoro/Harness-devkit --skill multi-agent
Clone the repo
git clone --depth 1 https://github.com/LuisFelipeMoro/Harness-devkit

Made for: Claude Code, Codex.

Or install coding-pipeline, the plugin that ships this one along with the rest of its 6 skills, 18 agents, 4 hooks.

Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,215 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00085 $0.01215
Opus 5 $0.00043 $0.00607
Sonnet 5 $0.00017 $0.00243
Haiku 4.5 $0.00009 $0.00121

Measured 3d ago against content hash 3a39a2aa73b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

multi-agent 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 3d 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.

plugins/coding-pipeline/skills/multi-agent/SKILL.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run the full multi-agent coding pipeline. If no task is provided, ask first.

Contract

  • Input: a feature/epic description (ask if not provided).
  • Output: implemented, tested epics with Review/Stress/QA/Verdict scores; a [{key}]-prefixed PROGRESS.md entry per epic; DevOps artifacts on final PRODUCTION READY; a PR from release/{slug}-{key} to main.
  • Boundary: Coder owns tests + implementation, written against the Architect's frozen Test Case table and falsified before handoff; Reviewer/StressTester run only after QA approval or escalation; unmitigated CRITICAL security is automatic NOT READY.
  • Done when: the Pipeline Summary prints after the final epic's Verdict with Security Gate, Falsification evidence, and Coverage shown.

Model assignment (see CLAUDE.md Model assignment table): dispatch the Architect on opus; Analyst, PM, Scrum Master, QA, Reviewer, Stress, Verdict, and the orchestrator on sonnet; the Coder (core + backend/frontend overlay), Tuner, DevOps, and any read-only Explore/mapping sub-agent on haiku. Don't run exploration on opus or the Architect's design pass on haiku.


Phase 0 — Delivery setup (once, before planning)

Derive the delivery slug + key from the feature name, create .worktrees/dlv-{key}/ on release/{slug}-{key}, and run everything inside it. An existing worktree for the key means resume (read the delivery file's Status + [{key}] PROGRESS.md entries), not recreate. Ask before the first git push. Never commit or merge to main — the terminal step is a PR from the release branch. Commands, header block, and branch rules: ../../references/delivery-and-worktree.md.


Phase 1 — Planning (once)

Load and follow skills/planning/SKILL.md (Phase 0 through Phase 4). Phase 2 (grill-me plan stress) and Phase 3 (human validation of unresolved questions) are mandatory before any coding.

  • If docs/deliveries/{key}/product-brief.md + PRD.md already exist (from a prior /analysis run for this key): load them and skip Phase 0 (inline analysis).
  • If the delivery file for this key already exists and was approved: skip Phases 0–2 and proceed directly to Phase 3 (Manifest).
  • On changes requested during human validation: update the delivery file → re-confirm before continuing.

Read the full file on GitHub · 70 lines

Files

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.

Changes

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.

  1. 3d ago First seen · 70 lines · 85 tokens per session scan A 3a39a2aa73b9

Subscribe to this mod's changes

multi-agent is a skill published in the GitHub repository LuisFelipeMoro/Harness-devkit (10 stars, last pushed 3d ago), licensed MIT. It adds 85 tokens to every session and 1,215 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens