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/harshanandak/forge/setupnpx skills add harshanandak/forge --skill setupgit clone --depth 1 https://github.com/harshanandak/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 | $0.00243 | $0.01097 |
| Opus 5 | $0.00121 | $0.00549 |
| Sonnet 5 | $0.00049 | $0.00219 |
| Haiku 4.5 | $0.00024 | $0.00110 |
Grade A, and why
setup 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Getting Forge installed, configured, upgraded, and diagnosed in a repo. These are the bootstrap and maintenance commands — distinct from the everyday workflow stages.
Install & configure
forge setup # interactive agent configuration (Claude/Cursor/Codex …)
forge setup --yes # non-interactive: accept defaults (use this in automation)
forge setup --agents claude,cursor --skip-external # target specific harnesses, skip service prompts
forge setup --path <dir> --dry-run # preview against another dir, write nothing
forge setup is interactive by default. In any automated/agent context pass --yes (or --non-interactive) so it never blocks on a prompt.
Initialize a fresh repo
forge init --minimal # shortcut for --profile minimal --yes
forge init --profile standard --harness claude,cursor
forge init --classification standard --dry-run # preview the adoption config
forge init writes the Forge adoption config (.forge/config.yaml). The profile picks how much enforcement ships on: minimal (rails off) → standard → full. This configures the workflow; toggling an individual gate afterward is the gates skill.
Diagnose
forge doctor # is the kernel DB on a cloud-synced / network path? (reliability signal)
forge doctor --json # machine-readable
forge doctor is narrow: it reports the filesystem class of the Forge kernel database path (local / cloud-synced / network) so you can catch the reliability footgun of running the DB on OneDrive/Dropbox/a network share. It is not a general health check.
Upgrade readiness
forge upgrade --dry-run # preview the planned self-heal, change nothing
forge upgrade # apply safe self-heal steps to make the repo upgrade-ready
forge upgrade previews and applies safe self-heal steps for Forge's own state. It does not update the installed npm package — use your package manager for that.
What ships with it
2 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.
- 2d ago First seen · 92 lines · 243 tokens per session scan A 38575e025b17
setup is a skill published in the GitHub repository harshanandak/forge (4 stars, last pushed 2d ago), licensed MIT. It adds 243 tokens to every session and 1,097 once invoked, about $0.0012 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.
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.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
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.