Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/LuisFelipeMoro/Harness-devkitnpx agentmods add skills/luisfelipemoro/harness-devkit/multi-agentWrote 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/luisfelipemoro/harness-devkit/multi-agent)<a href="https://agentmods.dev/skills/luisfelipemoro/harness-devkit/multi-agent"><img src="https://agentmods.dev/badge/skills/luisfelipemoro/harness-devkit/multi-agent/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/luisfelipemoro/harness-devkit/multi-agent"><img src="https://agentmods.dev/badge/skills/luisfelipemoro/harness-devkit/multi-agent.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 | $0.00107 | $0.01881 |
| Opus 5.5 | $0.00043 | $0.00752 |
| Sonnet 5.5 | $0.00021 | $0.00376 |
| Haiku 4.5 | $0.00011 | $0.00188 |
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 today.
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 — 96 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}]-prefixedPROGRESS.mdentry per epic; DevOps artifacts on final PRODUCTION READY; a PR fromrelease/{slug}-{key}tomain. - 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, Coverage and Duplication shown, and
/pr-reviewhas run on the opened PR and posted its findings.
Model assignment (see CLAUDE.md Model assignment table): dispatch the Architect on
opus; Analyst, PM, Scrum Master, Plan Reviewer, QA, Reviewer, Stress, Verdict, and the orchestrator onsonnet; the Coder (core + backend/frontend overlay), Tuner, DevOps, and any read-only Explore/mapping sub-agent onhaiku. 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.
If the main session is not on sonnet, say so and recommend /model sonnet (the Architect is still dispatched on opus by name).
If this session's prompt does not open with "You are the delivery orchestrator", print once, then continue (never stop):
"Exit, then run: claude --agent orchestrator, and inside it: /multi-agent {args}" ({args} = what the user passed here).
It pays off for multi-story or unattended deliveries, not a single small change, bug fix or quick question.
On one measured delivery (4e6020) the main thread was ~64% of cost, because it carries every agent's output on each call.
The orchestrator only dispatches and runs git and gates. Resume is lossless from the worktree + PROGRESS.md.
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.
- today Changed · +6 lines 1e5ea9e74a19
- 22d ago Changed · +6 lines c1db20979e0a
- 25d ago Changed · -14 lines 84e252f90729
- 1mo ago Changed · +2 lines · +22 tokens per session 7b114615d010
- 1mo ago Changed · +26 lines 39b864b10d29
- 1mo ago First seen · 70 lines · 85 tokens per session scan A 3a39a2aa73b9
multi-agent is a skill published in the GitHub repository LuisFelipeMoro/Harness-devkit (13 stars, last pushed today), licensed MIT. It adds 107 tokens to every session and 1,881 once invoked, about $0.0004 per session on Opus 5.5. 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
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.