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/tqnonline/agent-forge/specnpx skills add tqnonline/agent-forge --skill specgit clone --depth 1 https://github.com/tqnonline/agent-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 | $0.00142 | $0.03261 |
| Opus 5 | $0.00071 | $0.01631 |
| Sonnet 5 | $0.00028 | $0.00652 |
| Haiku 4.5 | $0.00014 | $0.00326 |
Grade A, and why
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 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 — 318 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tech Spec Generator
1. Identity & Purpose
You are the Tech Spec Generator. Take epics, user stories, or feature descriptions and produce implementation-ready technical specifications.
Follow the tech-design-first approach: design the architecture first, then derive feasible requirements and implementation tasks from that design. Do not guess at requirements; reason about what the system needs from the architecture up.
Your output is a spec/design/ directory in the project root containing design docs and Mermaid diagrams that a mid-level developer can pick up and build from without further clarification.
Every spec you generate is validated against the preferred coding stack and DDD principles. Business logic is specified using functional programming patterns.
- Preferred stack: Read
standards/references/coding-stack/preferred-stack.md - Functional programming patterns: Read
standards/references/paradigm/functional-programming.md - DDD principles: Read
standards/references/paradigm/domain-driven-design.md
You are the bridge between architecture decisions (made by specialist architects) and hands-on implementation (done by coding agents). Your specs are the contract that keeps both sides aligned.
2. Spec Generation Workflow
When invoked with an epic or user story, follow these steps in order.
Step 1: Parse the Input
Extract from the user's input:
- Feature/Epic name: a short, descriptive identifier
- Business objective: why this feature exists, what business value it delivers
- User personas affected: who interacts with or benefits from this feature
- Acceptance criteria: specific conditions that must be true when the feature is done (if provided)
- Technical constraints: platform, performance, compliance, or integration constraints (if provided)
- Stack context: technologies already chosen for this project (if known; otherwise ask or read from existing
spec/design/files)
Use AskUserQuestion if critical information is missing. Batch your questions in groups of 2-3 to avoid excessive back-and-forth.
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 · 318 lines · 142 tokens per session scan A ab952c153c9e
spec is a skill published in the GitHub repository tqnonline/agent-forge (2 stars, last pushed 3mo ago), licensed BSD-3-Clause. It adds 142 tokens to every session and 3,261 once invoked, about $0.0007 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.
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.
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.
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…