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 alphabetc1/agent-skills --skill forgegit clone --depth 1 https://github.com/alphabetc1/agent-skillsWrote 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/alphabetc1/agent-skills/forge)<a href="https://agentmods.dev/skills/alphabetc1/agent-skills/forge"><img src="https://agentmods.dev/badge/skills/alphabetc1/agent-skills/forge.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 | $0.00067 | $0.02632 |
| Opus 5 | $0.00034 | $0.01316 |
| Sonnet 5 | $0.00013 | $0.00526 |
| Haiku 4.5 | $0.00007 | $0.00263 |
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 6d 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 — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Forge
Overview
Run this skill only when the current user request explicitly invokes forge or $forge. If the request merely resembles a staged coding task, do not use Forge.
Advance the work from the detected starting stage through stage 5 in one invocation unless the user explicitly asks to stop after a specific stage.
Do not implement code before stage 4.
Write prompt.md, research.md, plan.md, and review.md in the language of the current user request. Keep source code, identifiers, and code comments in English.
Create or update all stage files in the current working directory.
Forge requires subagent support for its intended stage 4 and stage 5 execution model. Do not silently collapse those stages back into a single-agent build-and-review flow.
Detect the Stage
Treat a stage file as the starting-stage resume signal only when the current user request explicitly includes the literal filename.
- If the request does not explicitly mention
prompt.md,research.md,plan.md, orreview.md, start at stage 1. - If the request explicitly mentions
prompt.md, start at stage 2. - If the request explicitly mentions
research.md, start at stage 3. - If the request explicitly mentions
plan.md, start at stage 4. - If the request explicitly mentions
review.md, start at stage 5.
After choosing the starting stage, continue through all later stages by default.
If the user explicitly asks to stop after a particular stage, to only generate a specific artifact, or to skip a later stage such as review, honor that narrower stop point.
If the user mentions one stage file as the resume point and a later stage file as the requested stop point or final output, treat that as a valid start-and-stop pair instead of an ambiguity.
If the user explicitly mentions multiple stage filenames and the intended starting point is ambiguous, ask which file should be treated as authoritative before changing anything.
Stage Announcement
Before starting each substantive stage, explicitly announce the active stage in one short line.
What ships with it
28 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.
- .gitignore 39 B
- agents/openai.yaml 472 B
- docs/launch.md 3.0 KB
- docs/releases/v0.1.0.md 1.3 KB
- examples/auth-refactor/plan.md 1.2 KB
- examples/auth-refactor/prompt.md 1.1 KB
- examples/auth-refactor/request.md 301 B
- examples/auth-refactor/research.md 944 B
- examples/auth-refactor/result.md 284 B
- examples/auth-refactor/review.md 690 B
- examples/new-export-feature/plan.md 1.3 KB
- examples/new-export-feature/prompt.md 1.3 KB
- examples/new-export-feature/request.md 284 B
- examples/new-export-feature/research.md 939 B
- examples/new-export-feature/result.md 399 B
- examples/new-export-feature/review.md 690 B
- examples/payment-webhook-bugfix/plan.md 1.2 KB
- examples/payment-webhook-bugfix/prompt.md 1.1 KB
- examples/payment-webhook-bugfix/request.md 252 B
- examples/payment-webhook-bugfix/research.md 847 B
- examples/payment-webhook-bugfix/result.md 275 B
- examples/payment-webhook-bugfix/review.md 730 B
- examples/README.md 745 B
- install.ps1 2.6 KB runs code
- install.sh 3.0 KB runs code
- LICENSE 10 KB
- README.md 8.6 KB
- scripts/revert_stage_commits.py 6.0 KB runs code
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.
- 6d ago First seen · 218 lines · 67 tokens per session scan A 7df2ebcae225
forge is a skill published in the GitHub repository alphabetc1/agent-skills (2 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 67 tokens to every session and 2,632 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…