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 skills add ForgeyClap/claude-forge --skill forge-coregit clone --depth 1 https://github.com/ForgeyClap/claude-forgeWrote 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/forgeyclap/claude-forge/forge-core)<a href="https://agentmods.dev/skills/forgeyclap/claude-forge/forge-core"><img src="https://agentmods.dev/badge/skills/forgeyclap/claude-forge/forge-core.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 5.1 | $0.00065 | $0.09438 |
| Opus 5 | $0.00032 | $0.04719 |
| Sonnet 5 | $0.00013 | $0.01888 |
| Haiku 4.5 | $0.00006 | $0.00944 |
Grade A, and why
forge-core 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 5d 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 — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Forge Core (global, lightweight)
This is the global, security-light Forge layer. It carries instructions only — no hooks, no security gates, nothing that runs automatically across your projects. The full Forge V2 (command + skills + playbooks) is installed per project via the installer below.
What Forge does (Lead-Agent studio)
Lead Agent (you) → Mission Blueprint + Skill Discovery → dynamic role-based subagents (ECC-first, incl. custom roles) → outputs/artifacts → Lead Review → rework/fix loop → merge → optional Codex review → quality gate → honest forge-report. The Lead Agent plans before executing and decides the agents and skills — the role/skill examples in the playbooks are guidance, not fixed menus or limits. Pick the smallest relevant team; small task = small team, large/high-end = larger swarm. Don't lock to a fixed number; don't over-spawn to look impressive.
Skill Discovery + custom subagents/skills (Lead has final control)
Before assigning subagents the Lead Agent runs Skill Discovery: inspect the user mission, project type, files/frameworks/tools, package/config, project memory/profile, existing project-local skills, global Forge skills, available ECC agents/skills, MCP/tools, quality target, required outputs, and risks. It then discovers, chooses, assigns, or creates the right skills per project (not just "use the listed ones"). For unknown project types, create a custom taxonomy + custom subagents + custom-skill strategy — never force-fit into website/n8n/RAG/scraping. Skill gaps: create a safe project-local custom skill (.claude/skills/<name>/SKILL.md, scoped + documented + linked to a real work package), or a scaffold for approval, or a labeled native fallback, or mark BLOCKED. No executable subagent runs without an assigned skill/method. Every subagent + custom role + custom skill must be real (reason + work package + output or honest BLOCKED) and visible in dashboard/ledger/report — never fake one.
What ships with it
3 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.
- 5d ago First seen · 229 lines · 0 tokens per session scan E c39cc18bc910
forge-core is a skill published in the GitHub repository ForgeyClap/claude-forge (2 stars, last pushed 1mo ago), licensed MIT. It adds 65 tokens to every session and 9,438 once invoked, about $0.0003 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.
Other skills, from other repositories
flame-harness-evaluator
Phase 6 — skeptical QA. Run the game, watch it, then judge against the contract. Default = functional check; --strict adds quality and edge-case passes.
flame-harness-admob
Phase 7 — analyze the game, decide a rewarded-ad strategy, guide manual AdMob ad-unit creation, and inject googlemobileads + ATT/UMP consent code.
flame-harness-design
Phase 3 — define the Flutter designtokens.dart spec (palette, typography, spacing), the game's art/visual concept, and the asset/audio sourcing plan.
flame-harness-screenshot
Phase 9 — capture store screenshots in the game's configured locales via integrationtest (ads hidden), fill ASO keywords, and upload via fastlane.
flame-harness-submit
Phase 10 — upload store text metadata + categories via fastlane, then pause with exact manual steps for the final iOS review submission and Android production promotion.
flame-harness-contract
Phase 4 — propose verifiable completion criteria and mandatory hard gates; reach AGREED (1-pass default, multi-round negotiation in --strict).