Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/tesslio/spec-driven-development-tilenpx agentmods add skills/tesslio/spec-driven-development-tile/spec-writerWrote 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/tesslio/spec-driven-development-tile/spec-writer)<a href="https://agentmods.dev/skills/tesslio/spec-driven-development-tile/spec-writer"><img src="https://agentmods.dev/badge/skills/tesslio/spec-driven-development-tile/spec-writer/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/tesslio/spec-driven-development-tile/spec-writer"><img src="https://agentmods.dev/badge/skills/tesslio/spec-driven-development-tile/spec-writer.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 | $0.00085 | $0.00740 |
| Opus 5.5 | $0.00034 | $0.00296 |
| Sonnet 5.5 | $0.00017 | $0.00148 |
| Haiku 4.5 | $0.00009 | $0.00074 |
Grade A, and why
spec-writer 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 2mo 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec Writer
Create and maintain .spec.md files that capture functional requirements and link to their verification tests.
When to use
- After
requirement-gatheringproduces confirmed requirements - When existing specs need updating due to changed requirements
- When implementation revealed gaps that need documenting
Steps
-
Determine scope. Decide whether to create a new spec or update an existing one. One spec per logical unit of functionality — don't combine unrelated features.
-
Write frontmatter. Every spec requires YAML frontmatter:
--- name: Feature Name description: Brief description of what this spec covers targets: - ../src/path/to/implementation.py - ../src/path/to/related/**/*.py ---name: Human-readable feature namedescription: One-line summarytargets: Relative paths or glob patterns to implementation files. At least one required.
-
Document requirements. Write clear, scannable requirements:
- Start with an API contract code block if there's a public interface
- Use headings to organize by feature area
- Be specific about expected behavior and edge cases
- Describe error handling expectations
-
Link tests. Add
[@test]links inline, next to the requirements they verify:- Invalid passwords return 401 `[@test] ../tests/test_auth_invalid_password.py` -
Review against styleguide. Check the spec against the Spec Styleguide: concise, scannable, context around test links, clear headings, specific about behavior, granular test files.
-
Save the spec. Place spec files in the project's
specs/directory with a.spec.mdextension.
Complete example
---
name: Shopping Cart
description: Add, remove, and checkout operations for the shopping cart
targets:
- ../src/cart.py
- ../src/checkout.py
---
# Shopping Cart
## Core operations
```python
def add_item(cart_id: str, product_id: str, quantity: int) -> Cart: ...
def remove_item(cart_id: str, product_id: str) -> Cart: ...
def checkout(cart_id: str, payment_method: str) -> Order: ...
[@test] ../tests/cart/test_cart_operations.py
Quantity rules
- Quantity must be >= 1; values <= 0 raise
ValueError[@test] ../tests/cart/test_quantity_validation.py - Adding an existing item increments quantity instead of duplicating
[@test] ../tests/cart/test_add_existing_item.py
Checkout
- Empty cart raises
CheckoutError[@test] ../tests/cart/test_empty_checkout.py - Out-of-stock items are removed and the user is notified
[@test] ../tests/cart/test_stock_check.py
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.
- 2mo ago First seen · 99 lines · 85 tokens per session scan A 9471791132f4
spec-writer is a skill published in the GitHub repository tesslio/spec-driven-development-tile (57 stars, last pushed 7mo ago), licensed MIT. It adds 85 tokens to every session and 740 once invoked, about $0.0003 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.
spec-writer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| spec-writertesslio/spec-driven-development-tile | Skill | 57 | 7mo ago | MIT | A | 85 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |