agentmods.dev

forge

forge is a skill for Claude Code, Codex from Snowflake-Labs/cocoplus. It costs 42 tokens per session (680 once invoked), scanned A, original, MIT.

A command that runs CocoForge, a team-style workflow where specialized agents work through a stated goal in planned stages.

In plain words
What is it for?
Use it to start a bounded task or persistent goal, inspect its state, stop it safely, or resolve a disagreement between refinement steps.
Why use it?
It organizes planning, specialist work, critique, and progress tracking instead of leaving a complex goal as one unstructured task.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 720repo 9d ago A scan 42 tokens original MIT

Good fit Use it to start a bounded task or persistent goal, inspect its state, stop it safely, or resolve a disagreement between refinement steps.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/snowflake-labs/cocoplus/forge
View source ↗ Snowflake-Labs/cocoplus cocoplus.dev
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.

Any agent
npx skills add Snowflake-Labs/cocoplus --skill forge
Clone the repo
git clone --depth 1 https://github.com/Snowflake-Labs/cocoplus

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for forge

README.md
[![agentmods](https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/forge/github.svg)](https://agentmods.dev/skills/snowflake-labs/cocoplus/forge)
Your own site
<a href="https://agentmods.dev/skills/snowflake-labs/cocoplus/forge"><img src="https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/forge/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.

agentmods 80×15 button for forge

Your own site · 80×15
<a href="https://agentmods.dev/skills/snowflake-labs/cocoplus/forge"><img src="https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/forge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 680 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00042 $0.00680
Opus 5 $0.00021 $0.00340
Sonnet 5 $0.00008 $0.00136
Haiku 4.5 $0.00004 $0.00068

Measured 8d ago against content hash d3d9d4d1029a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

forge 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.

.cortex/skills/cocoforge/forge.skill.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Your objective is to operate CocoForge.

Modes

  • $forge "goal statement" starts Task Mode for a bounded goal.
  • $forge "goal statement" --ladder starts Task Mode with the refinement ladder enabled.
  • $forge goal "goal statement" starts Goal Mode, which persists across sessions.
  • $forge status reports current forge state.
  • $forge stop stops cleanly after the current phase and emits an early milestone gate.
  • $forge resolve-dispute exits a refinement-ladder deadlock and requests developer judgment.

Activation

When starting a forge:

  1. Verify .cocoplus/ exists.
  2. Create .cocoplus/modes/cocoforge.on.
  3. Write .cocoplus/lifecycle/forge-state.json with:
    • active: true
    • mode: "task" or "goal"
    • goal
    • iteration: 1
    • phase: "plan"
    • budget_status
    • team
    • history
  4. Append a forge_started event to .cocoplus/lifecycle/forge-activity.jsonl.
  5. If CocoPilot is active, record pilot_superseded: true.

Team Topology

CocoForge uses:

  • Team Lead: plans iterations, dispatches specialists, synthesizes outputs, writes milestone gates.
  • Quality Critic: default stance REJECT; approves only evidence that meets criteria.
  • Learning Curator: captures reusable patterns and specialist refinements.
  • Specialists: fixed or dynamic personas scoped to the iteration plan.

Refinement Ladder

When --ladder is enabled, the Quality Critic treats achieved rungs as floors. Default rungs are 85, 90, 95, and 99. If a later iteration drops below the current floor, the Critic rejects it even if it improves another dimension. After two failed fix cycles at the same rung, the forge enters dispute state and requires $forge resolve-dispute.

Milestone Gate

At every gate, output:

  • Goal criteria status
  • What changed
  • Quality Critic verdict
  • Budget status
  • Next iteration proposal
  • Developer decision requested

Exit Criteria

  • Forge state file exists.
  • Forge activity log has append-only events.
  • CocoPilot resumes after forge stop if it was active before forge activation.
  • Ladder sessions preserve the current floor, score trend, and dispute state in forge-state.json.

Read the full file on GitHub · 75 lines

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. 8d ago First seen · 75 lines · 42 tokens per session scan A d3d9d4d1029a

Subscribe to this mod's changes

forge is a skill published in the GitHub repository Snowflake-Labs/cocoplus (720 stars, last pushed 9d ago), licensed MIT. It adds 42 tokens to every session and 680 once invoked, about $0.0002 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 2026-09-03.

Building agentsLLMPlanningagentsagentskillscocoforgecocopluscortexcortexaisnowflakev2
Related

Other skills, from other repositories

prompt-engineering

Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use when optimizing prompts, improving LLM outputs, designing production prompt templates, or building AI-powered features.

wpank/ai · 44 tokens

openkb-html-critic

Use to review a generated HTML deck or single-page artifact for visual quality and structural correctness. Especially good at catching CSS specificity bugs where slide-modifier classes (.divider, .center, .q, .flow etc.) accidentally override the base .slide{display:none} and cause one slide to stack on top of every…

VectifyAI/OpenKB · 132 tokens

cron

Schedule, list, pause, resume, edit, or run the user's agentica cron jobs with the cronjob tool. Use when asked to remind, schedule a recurring or one-shot task, try a job now, or manage jobs that fire unattended.

shibing624/agentica · 52 tokens

terraform

Operate Terraform and OpenTofu across the whole infrastructure lifecycle: module structure, state backends and locking, plan/apply workflow, drift detection, remote state, upgrade and refactor flows, and evidence-based diagnostics. Use when running or inspecting terraform plans, applies, state files, imports, or state…

magnus919/agent-skills · 96 tokens

go-to-market

Plan and evaluate go-to-market strategy using positioning, acquisition, growth economics, market-entry, and competitive-response workflows. Do not use for CRM execution, product strategy, legal interpretation, or visual brand design. (April Dunford's positioning, message hierarchy), customer acquisition strategy…

magnus919/agent-skills · 135 tokens

zcfg

Integrate zcfg (Zero Dependency Configuration Utility) into Java applications. Use when adding configuration loading, reading properties files, setting up application configuration, or integrating zcfg into a Java project. Triggers on "zcfg", "add configuration", "load properties", "application configuration with…

AdamBien/airails · 75 tokens