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/forgeyclap/claude-forge/forge-fullstacknpx skills add ForgeyClap/claude-forge --skill forge-fullstackgit clone --depth 1 https://github.com/ForgeyClap/claude-forgeWhat 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 | $0.00045 | $0.00565 |
| Opus 5 | $0.00023 | $0.00282 |
| Sonnet 5 | $0.00009 | $0.00113 |
| Haiku 4.5 | $0.00005 | $0.00056 |
Grade A, and why
forge-fullstack 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 2d 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Forge playbook — Full-stack app
Do not duplicate ECC skills — defer to: make-plan/do (planning+execution), using-git-worktrees (parallel isolation), subagent-driven-development. Orchestration only.
Hard rules
- Auth on every protected route, enforced server-side (authn + authz).
- Input validation on every endpoint; never trust client data.
- Secrets in env +
.env.exampleplaceholders; no secrets in the client bundle. - DB migrations reviewed by
database-reviewerand reversible. - Auth/secret/DB changes are a required Codex review area — force
/codex:adversarial-review.
Team (conditional by stack/level)
- Lead:
architect+planner. - Frontend:
react-reviewer/vue-reviewer. - Backend:
fastapi-reviewer/django-reviewer(Python) ortypescript-reviewer/go-reviewer(by stack). - Data:
database-reviewer(Postgres/Supabase). - Cross-cutting:
security-reviewer,tdd-guide,e2e-runner/production-validator.
Skills / commands / MCP
make-plan→do, using-git-worktrees, language build/test commands (/react-build, /python-review, etc.), /test-coverage, security-reviewer. Supabase/Shopify MCP via ToolSearch if relevant.
Fan-out & flow
L3 standard; L4 for a platform / prod client delivery (phased, review after each phase). Serial: plan → DB schema + API contract first → integration → e2e → security → review. Parallel: frontend ∥ backend ∥ schema in separate worktrees; you integrate. Don't let two agents write the same tree.
Domain gates
Auth flow tested (signup/login/logout/refresh); validation on all endpoints; migrations clean on a fresh DB; e2e green; no folder mixing.
Ship-readiness (unique)
Migrations run clean on a fresh DB; auth flow verified; .env.example complete; no secrets in repo; rollback/seed documented; dev/preview by default (production needs explicit user approval). The ship-readiness full-stack/auth checklist is advisory; optionally run codex-reviewer (Codex) on auth/migration code — not a blocker.
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.
- 2d ago First seen · 37 lines · 45 tokens per session scan A c04cf859fdf3
forge-fullstack is a skill published in the GitHub repository ForgeyClap/claude-forge (2 stars, last pushed 29d ago), licensed MIT. It adds 45 tokens to every session and 565 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 2026-08-31.
Other skills, from other repositories
zh-output-example
Reviews Chinese skill documentation for publication readiness. Invoke when the user asks in Chinese to review a skill.
argent-tv-interact
Control and inspect TV apps via argent — Apple TV (tvOS), Android TV (leanback), and Amazon Fire TV (Vega). Boot the target, read focus, navigate with the D-pad remote, type, screenshot, and on Vega debug the JS runtime (evaluate, console logs, network inspector). Use when a task targets a TV (runtimeKind "tv", or…
review-offered-task
Review a task that has been offered to you and decide whether to accept or reject it.
company-hiring-intelligence
Reverse-engineer what a company is building by scraping their job postings, careers page, LinkedIn Jobs, and engineering blog using TinyFish web agents. Use whenever a user wants to understand a company's strategic direction from hiring signals, do competitive intelligence, figure out a tech stack from job…
文档协作
引导用户通过结构化的文档共同编写工作流程。当用户想撰写文档、提案、技术规范、决策文档或类似结构化内容时使用。该工作流程帮助用户高效传递上下文，通过迭代优化内容，并验证文档对读者有效。当用户提到写文档、创建提案、起草规范或类似文档任务时触发。.
aidd-dev:08:for-sure
Iterative agent loop that tracks attempts and retries until a success condition is met. Use when the user says "for sure", "make sure", "keep trying until", "loop until done", "don't stop until", or needs guaranteed completion of a task with explicit success criteria.