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 ivan-szz/spec-writer-skill --skill spec-writer-setupgit clone --depth 1 https://github.com/ivan-szz/spec-writer-skillWrote 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/ivan-szz/spec-writer-skill/spec-writer-setup)<a href="https://agentmods.dev/skills/ivan-szz/spec-writer-skill/spec-writer-setup"><img src="https://agentmods.dev/badge/skills/ivan-szz/spec-writer-skill/spec-writer-setup.svg" alt="Measured on agentmods" 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 | $0.00062 | $0.05760 |
| Opus 5 | $0.00031 | $0.02880 |
| Sonnet 5 | $0.00012 | $0.01152 |
| Haiku 4.5 | $0.00006 | $0.00576 |
Grade A, and why
spec-writer-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 8d 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 — 536 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Adapter Skill
Scan a project to extract its idiomatic patterns, then generate customized TDD agents that speak the project's language instead of pseudocode. This bridges the gap between the generic Red/Green/Refactor agents and a real codebase's conventions.
Core Principle
The best TDD agent is one that looks like it was written for your project. Generic agents say "adapt to your stack" — this skill does the adaptation automatically by reading what your project actually does.
Setup
Before doing anything:
- Locate the target project. If a path is given, use it. Otherwise, ask the user which project to scan.
- Read the base TDD agents. Load
tdd-red,tdd-green, andtdd-refactorfrom theagents/directory. These are the templates to customize. - Check for prior context. Look for an existing
context-report.mdin the target project. If found, ask the user whether to re-scan or use the existing report.
Commands
| Command | Description |
|---|---|
scan [path] |
Gather project context, produce a pattern report |
adapt [agent|all] |
Generate customized TDD agent(s) from the last scan |
scan-and-adapt [path] |
Full pipeline: scan then adapt all three agents |
Routing
- No argument: ask the user which command and which project path.
- First word matches a command: load and execute it.
adaptwithout a prior scan: runscanfirst, then adapt.adapt redoradapt tdd-red: customize only the Red Phase agent.adapt all: customize all three agents.
Phase 1 — Scan
The scan phase reads the target project and extracts a structured context report. This is the foundation for all customization.
1.1 Discovery
Scan the project root for these files, in order of priority:
Documentation & Conventions (read first — highest signal):
| File | What it reveals |
|---|---|
README.md |
Tech stack, setup commands, project purpose |
AGENTS.md, CLAUDE.md, COPILOT.md, .cursorrules, .windsurfrules, .clinerules |
Existing AI agent instructions and conventions |
CONTRIBUTING.md |
Code style, PR conventions, testing requirements |
docs/ directory |
Architecture decisions, API docs, design docs |
specs/ directory |
Existing specifications and their structure |
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.
- 8d ago First seen · 536 lines · 62 tokens per session scan A 3f7d0aa877e2
spec-writer-setup is a skill published in the GitHub repository ivan-szz/spec-writer-skill (1 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 62 tokens to every session and 5,760 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
engram-testing-coverage
TDD and coverage standards for Engram. Trigger: When implementing behavior changes in any package.
nw-fp-clojure
Clojure language-specific patterns, data-first modeling, REPL-driven development, and spec.
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.
mobiai-mobile-tdd
You MUST use this before writing any implementation code for a mobile feature, bug fix, refactor, or behavior change. Tests come before implementation — no exceptions.
tdd
This skill should be used when the user wants to implement features or fix bugs using test-driven development. Enforces the RED-GREEN-REFACTOR cycle with vertical slicing, context isolation between test writing and implementation, human checkpoints, and auto-test feedback loops. Uses multi-agent orchestration with the…
conductor-implement
Execute tasks from a track's implementation plan following TDD workflow.