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 firatcand/forge --skill forgegit clone --depth 1 https://github.com/firatcand/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/firatcand/forge/forge)<a href="https://agentmods.dev/skills/firatcand/forge/forge"><img src="https://agentmods.dev/badge/skills/firatcand/forge/forge/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/firatcand/forge/forge"><img src="https://agentmods.dev/badge/skills/firatcand/forge/forge.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00036 | $0.00778 |
| Opus 5.5 | $0.00014 | $0.00311 |
| Sonnet 5.5 | $0.00007 | $0.00156 |
| Haiku 4.5 | $0.00004 | $0.00078 |
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 1mo 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/forge
Take a product idea — a sentence in the user's head — and turn it into a structured spec/BRIEF.md that everything downstream draws from.
Forge suggests, never interrogates. It does not question whether the user should build the idea or what their advantage is. It clarifies what they want to build and surfaces structure.
When invoked
User runs /forge (no args) at the start of a new project, OR /forge --refine [section] to re-run on a section of an existing BRIEF.md.
The 4 product questions
Ask all four. Keep them tight. If an answer is vague, ask up to 2 follow-ups before moving on. Do not push back on the value of the idea — only on the clarity of intent and scope.
Q1 — What is it, and who uses it?
"In one or two sentences, what does this product do? Who is the target user, and what's the situation when they reach for it?"
If the answer is abstract ("a platform for X"), ask for a concrete moment — the last time someone hit the problem this product solves and what they did instead.
Q2 — The smallest valuable thing (v1 scope)
"What is the smallest version of this that's still worth using? Strip everything optional. What remains?"
Force a v1 cut. Anything beyond v1 goes to "open unknowns" or "later".
Q3 — Non-goals
"What will this product NOT do, even when tempting? Where's the scope trap?"
Need at least 2 concrete non-goals. If the user can't list any, the v1 scope is under-defined — re-ask Q2.
Q4 — Open unknowns
"What's still fuzzy? What decisions are you deferring? What are you assuming that you'd want to validate before/during build?"
Capture these — they feed /draft-prd and /draft-spec.
What forge does NOT ask
Forge does not ask: "Why you?", "Why now?", "What's your unfair advantage?", "What's your kill criteria?", "What's your north-star metric?". These are founder-validation questions and don't belong in an engineering-delivery framework. Forge assumes the user has already decided to build.
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.
- 1mo ago First seen · 83 lines · 36 tokens per session scan A abe8494b2cb8
forge is a skill published in the GitHub repository firatcand/forge (13 stars, last pushed 2mo ago), licensed MIT. It adds 36 tokens to every session and 778 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
ospec-change
Create or advance a lightweight OSpec change using the classic fast workflow.
design
Set visual and interaction direction for any UI surface (web, React, TUI, CLI, desktop, Qt, design-system tokens) before any UI code. Direction-first: generates 3-4 distinct directions via verbalized sampling, picks one via per-axis single-select, then derives palette, typography, spacing, motion budget. Loads when…
askme
Verbalized Sampling (VS) protocol for intent exploration before planning, mode-aware. Default exhaustive runs full VS; collaborative runs tip-sharing dialogue; adversarial walks the design tree one fork at a time. Auto-detects from phrasing ("help me refine" → collaborative, "poke holes" → adversarial); override via…
grill-me
Adversarial relentless interview against any plan or design until shared understanding is reached. Walk the decision tree, resolve dependencies one answer at a time, recommend a default per question. Trigger when the user says "grill me", "stress-test this", "interview me about this design", or otherwise asks for…
fix
Polymorphic iterative repair loop — accept a verifier failure, structured findings (review/resolve/triage-issue), or a bug description; modify→verify→keep on green, auto-revert on guard regression, until clean or iteration cap. Use when the user says "fix", "make it pass", or "apply the findings", or hands an artifact…
git-branchless
Enforce idiomatic git-branchless during planning and executing tasks — detached-HEAD-first work, in-memory rebase via git move, event-log recovery via git undo, deferred branch creation, speculative-merge git sync for base updates. Use when planning or executing multi-commit work, history rewrites, stack edits…