A guided starting step for Forge, a project-workflow tool. It checks what kind of codebase you are in, whether Forge is set up, and whether the folder is a Git repository before offering setup.

Use it at the beginning of a fresh session, in a new project, or when asking whether Forge is active. It helps inspect the project and decide whether to initialize Forge.

It prevents an agent from changing a project before understanding its current state. It also makes clear when Forge has not yet been initialized.

activation — Skill for Claude Code and Codex by harshanandak: A guided starting step for Forge, a project-workflow tool.

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.

agentmods

npx agentmods add skills/harshanandak/forge/activation

Any agent

npx skills add harshanandak/forge --skill activation

Clone the repo

git clone --depth 1 https://github.com/harshanandak/forge

Made for: Claude Code, Codex.

Or install forge, the plugin that ships this one along with the rest of its 1 skill, 1 hook.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/harshanandak/forge/activation.svg)](https://agentmods.dev/skills/harshanandak/forge/activation)

Your own site

<a href="https://agentmods.dev/skills/harshanandak/forge/activation"><img src="https://agentmods.dev/badge/skills/harshanandak/forge/activation.svg" alt="Measured on agentmods" height="20"></a>

Per session 130 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 763 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00130	$0.00763
Opus 5	$0.00065	$0.00381
Sonnet 5	$0.00026	$0.00153
Haiku 4.5	$0.00013	$0.00076

Measured 4d ago against content hash a150e3bd4f32, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

activation 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.

plugin/skills/activation/SKILL.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Forge activation (front door)

You are orienting a project where Forge is available (installed as a global plugin or an npm dev-dep) but not yet engaged. Your job is to orient first, then offer — never force. This skill creates nothing by itself; a mutating forge verb is what lazily initializes .forge/.

Orient first (state findings BEFORE offering)

Run read-only checks, then STATE what you found in one short paragraph before you offer any setup. Do not opine or prescribe before you have looked.

Is Forge initialized? test -d .forge && echo present || echo absent
What kind of project is this?
- package.json present → JS/TS project (note the package manager: bun/npm/pnpm/yarn lockfile).
- Markdown-heavy, no package.json → docs / planning repo.
- Otherwise → describe what you see (language, build files).
Is it a git repo? git rev-parse --is-inside-work-tree 2>/dev/null

Then say, in your own words: "Here's what this project looks like today: …" — project type, whether .forge/ exists, git status. Only after stating this do you offer anything.

Then offer the bare minimum (never forced)

Present setup as a conversational choice, not a mandate:

If .forge/ is absent: explain that Forge needs no setup step to be useful — read-only verbs (forge status, forge ready, forge show <id>) work immediately and write nothing. The first mutating verb (forge claim, forge create, forge remember) lazily creates a bare-minimum, gates-disabled .forge/ skeleton. Nothing heavier (git hooks, lefthook, protected paths, .mcp.json, scripts tree) is installed unless the user later runs forge setup.
If .forge/ is present: say so and route to the right stage instead — this skill's work is done.

Offer, then stop and let the user choose. Do not run forge setup or install hooks on their behalf unless they ask.

Terminal state → next step

This is a front-door primitive, not the full workflow. After orienting and offering:

Read the full file on GitHub · 63 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.

4d ago First seen · 63 lines · 130 tokens per session scan A a150e3bd4f32

Subscribe to this mod's changes

activation is a skill published in the GitHub repository harshanandak/forge (4 stars, last pushed 4d ago), licensed MIT. It adds 130 tokens to every session and 763 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.

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens