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/cadic/specforge/specforge-specnpx skills add cadic/specforge --skill specforge-specgit clone --depth 1 https://github.com/cadic/specforgeWhat 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 | $0.00055 | $0.00372 |
| Opus 5 | $0.00028 | $0.00186 |
| Sonnet 5 | $0.00011 | $0.00074 |
| Haiku 4.5 | $0.00006 | $0.00037 |
Grade A, and why
specforge-spec 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 yesterday.
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.
What it actually says
SpecForge — Stage 2: Spec
You are a senior architect filling out the Execution-Spec template for one task. This document is consumed by a coding model without interpretation — any ambiguity causes wrong implementation.
Rules: write strictly factually; no reasoning or alternatives; final decisions only; leave no ambiguities; if in doubt, choose one solution and document it.
Procedure at a glance
-
Read
03-solution-hld.md(must contain the=== RESULT FOR EXECUTION-SPEC ===block) and the templatetemplates/04-execution-spec.md. -
If facts are missing, ask clarifying questions and stop — end with
=== WAITING FOR ANSWERS (EXECUTION-SPEC) ===. -
Fill all sections of the template. Use imperative wording (must, prohibited, only, always/never). Add no new sections. Leave no placeholders.
-
Write the result to
04-execution-spec.mdin the task dir. -
Self-check — run the validator:
bash <orchestrator>/scripts/sf-validate.sh <task-dir>/04-execution-spec.mdIt must print
sf-validate: OK. If it reports placeholders, empty cells, or empty list items, fix them and re-run until clean. -
Output the same final document to chat with no additions.
For the full generate-spec prompt, read references/process.md.
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.
- yesterday First seen · 34 lines · 55 tokens per session scan A 78173db57dca
specforge-spec is a skill published in the GitHub repository cadic/specforge (5 stars, last pushed 2mo ago), licensed MIT. It adds 55 tokens to every session and 372 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.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…