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 agentmods add skills/mgiovani/cc-arsenal/team-implementnpx skills add mgiovani/cc-arsenal --skill team-implementgit clone --depth 1 https://github.com/mgiovani/cc-arsenalWrote 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/mgiovani/cc-arsenal/team-implement)<a href="https://agentmods.dev/skills/mgiovani/cc-arsenal/team-implement"><img src="https://agentmods.dev/badge/skills/mgiovani/cc-arsenal/team-implement.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 | $0.00121 | $0.04158 |
| Opus 5 | $0.00060 | $0.02079 |
| Sonnet 5 | $0.00024 | $0.00832 |
| Haiku 4.5 | $0.00012 | $0.00416 |
Grade A, and why
team-implement 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 4d 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 — 380 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Team Implement
Adaptive spec-driven development team that scales from 3 agents (lite) to ~9 (full) based on project complexity. All planning completes before any code changes, with explicit user approval between planning and implementation.
Prerequisites & fallback chain: read this first
Full mode needs multi-agent teams. In Claude Code that requires:
CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1
With the flag set, full mode spawns named teammates via the Task tool with a team_name (the team itself is created implicitly by the first such call, there's no separate "create team" step), coordinates via SendMessage, and stops a teammate with TaskStop. The exact tool signatures depend on the environment you're running in: treat any call shown below as illustrative and use whatever the local Task/SendMessage/TaskStop equivalents actually are. Do not invent a Teammate tool or similar if nothing like it exists here.
No flag, or a Task ... team_name call fails? Fall back to Lite mode: identical phase structure, but roles run as sequential Task subagents (no team_name, no cross-agent messaging) instead of a coordinated team.
No Task/subagent tool at all? Fall back further still: run every phase's steps yourself, inline, sequentially. The phase → gate → phase structure below is the workflow: teams and subagents are just two ways to parallelize it.
Delegate mode (Claude Code, full mode): Shift+Tab restricts the lead to coordination-only tools. Without it, wait for teammates to finish before touching their files yourself.
Input
$ARGUMENTS
Known Limitations
- No session resumption: an interrupted session loses spawned teammates (full mode)
- One team per session; teammates cannot spawn their own sub-teams
- Teammates sometimes forget to mark tasks complete: poll
TaskListrather than trusting silence - Teammates load project CLAUDE.md/AGENTS.md automatically (a benefit, not a limitation)
Workflow Overview
MACRO PHASE A: PLANNING (no code changes)
Phase 0: Input Ingestion & Discovery
Phase 1: Clarifying Questions
Phase 2: Specification
Phase 3: Architecture & Design
Phase 4: Adversarial Review
Phase 5: Task Decomposition
══════════════ USER APPROVAL GATE ══════════════
MACRO PHASE B: IMPLEMENTATION (code changes)
Phase 6: Implementation
Phase 7: Quality Assurance
Phase 8: Documentation & Delivery
Phase 9: Teardown
What ships with it
6 files 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.
- 4d ago First seen · 380 lines · 121 tokens per session scan A 40d5e75ecfa4
team-implement is a skill published in the GitHub repository mgiovani/cc-arsenal (7 stars, last pushed 4d ago), licensed MIT. It adds 121 tokens to every session and 4,158 once invoked, about $0.0006 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
pod-init
Initialize CocoPlus project bundle in the current directory. Creates .cocoplus/ directory structure, copies all templates, initializes AGENTS.md, project.md, flow.json, and creates the initial git commit. Run this once per project before using any other CocoPlus command.
cocoharvest
Decompose an approved plan into parallel workstreams, assign specialist personas, classify stages as HITL or AFK (CocoLens), generate flow.json stages with checkpoints and dual-file state, and create per-stage prompt files. Includes adaptive parallelism, stall detection, shell identity injection, and consecutive…
plan
Enter the Plan phase of CocoBrew. Runs CocoSpec quality gate pre-flight, reads spec.md and discuss.md (if present), invokes Coco native plan mode as a mandatory gate, captures the approved plan to plan.md, creates initial flow.json template, and commits. Must have $spec completed first.
cococonverge
CocoPivot — multi-pod convergence synthesizer. Deterministically deduplicates findings from N parallel pod outputs into one prioritized, coordinated action plan. Invoked via $pivot run/show/status/clear.
cocoplus-config
CocoPlus configuration SSOT — $cocoplus sync propagates cocoplus.toml into downstream artifacts; $cocoplus migrate-config converts legacy safety-config.json. Invoked via $cocoplus sync and $cocoplus migrate-config.
lean-debt
CocoLean shortcut debt ledger — harvests cocoplus: comment markers across the CocoPod and produces a ranked deferral report sorted by ceiling imminence and age.