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 dayvisonassis/sdd-skills --skill spec-writergit clone --depth 1 https://github.com/dayvisonassis/sdd-skillsWrote 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/dayvisonassis/sdd-skills/spec-writer)<a href="https://agentmods.dev/skills/dayvisonassis/sdd-skills/spec-writer"><img src="https://agentmods.dev/badge/skills/dayvisonassis/sdd-skills/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/dayvisonassis/sdd-skills/spec-writer"><img src="https://agentmods.dev/badge/skills/dayvisonassis/sdd-skills/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 | $0.00072 | $0.08261 |
| Opus 5.5 | $0.00029 | $0.03304 |
| Sonnet 5.5 | $0.00014 | $0.01652 |
| Haiku 4.5 | $0.00007 | $0.00826 |
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 16d 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 — 505 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feature Specs Writer
Generate implementation-ready technical specifications based on the project's PRD and existing codebase patterns. Besides spec.md and plan.md, it produces a third artifact, contract.md — the operational contract consumed by implement-feature (which must satisfy it) and by evaluator (which validates against it).
Base docs (in this package):
https://github.com/dayvisonassis/sdd-skills/blob/main/docs/Contrato_de_Feature.md(contract structure),https://github.com/dayvisonassis/sdd-skills/blob/main/docs/Como_criar_gates.md(gates), andhttps://github.com/dayvisonassis/sdd-skills/blob/main/docs/ARQUITETURA_DAS_SKILLS.md(full flow). Start withhttps://github.com/dayvisonassis/sdd-skills/blob/main/docs/GUIA_DO_WORKFLOW.mdfor how the skills fit together.
The skill has two modes:
- Single-feature mode (default): operates on one feature at a time, identified by its PRD feature ID (F01, F02...), with an interactive interview (Steps 1–6 below).
- Batch mode: operates on multiple features from the same wave in parallel, auto-accepting all interview recommendations. Activated automatically when the input contains multiple IDs, a wave reference, or a mix. See the Batch Mode section near the end of this file.
Output: THREE files are required:
spec.md- Technical specification (7 sections)plan.md- Implementation plan (phases and steps)contract.md- Operational contract (environment, quality gates, coverage manifest, observable criteria)
Output location: docs/<feature-id>-<kebab-name>/{spec.md,plan.md,contract.md}
- The
<kebab-name>is derived from the feature's name in the PRD Section 6 (lowercase, spaces → hyphens, special characters removed). Example:F03. Video Upload→docs/F03-video-upload/.
Execution Steps (6 Steps)
Note: These are internal agent execution steps. The OUTPUT plan document will have 1-5 phases based on feature complexity.
Step 1: Resolve Input and Pre-Analysis
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.
- 16d ago Changed · +4 lines 11b6ff6c2f50
- 18d ago Changed c7fe4902f315
- 29d ago Changed · +4 lines aebc8d0e11db
- 1mo ago Changed · +14 lines 3e2956784e80
- 2mo ago First seen · 483 lines · 72 tokens per session scan A e9207d1767aa
spec-writer is a skill published in the GitHub repository dayvisonassis/sdd-skills (3 stars, last pushed 16d ago), licensed MIT. It adds 72 tokens to every session and 8,261 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 2026-08-31.
Other skills, from other repositories
exploratory-data-analysis
Performs bounded, local exploratory analysis of explicitly supported scientific files. Supports redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
webhook-management
Configure and validate CCAM webhook targets across supported chat, incident, automation, and generic providers. Use when listing provider requirements, creating or updating a target, scoping it to alert rules, sending a test notification, reviewing delivery history, or deleting a target.
design-review
Review a web app or page for visual design quality — layout, typography, spacing, colour, hierarchy, consistency, interaction patterns, and responsive behaviour. Not a UX audit (that checks usability) — this checks whether it looks professional and polished. Produces a design findings report with screenshots.…
react-patterns
React 19 performance patterns and composition architecture for Vite + Cloudflare projects. 50+ rules ranked by impact — eliminating waterfalls, bundle optimisation, re-render prevention, composition over boolean props, server/client boundaries, and React 19 APIs. Use when writing, reviewing, or refactoring React…
render-3d-product-showcase
Assemble a premium 3D product-showcase ad from a config — four beat clips (an orbiting hero rotation, a macro push-in, a physics reveal, a typographic close) normalized to the chosen backdrop colour, hard-concatenated in order, closed on a deterministic Playwright brand end card, and mixed under one instrumental bed…
render-airdrop-carousel
Assemble a viral iOS "AirDrop" notification-carousel video ad (≈6–8s, 9:16) from a brand line plus 6–16 real product photos — a native AirDrop share-sheet card ("Brand would like to share a · Decline / Accept") springs up and its preview window CYCLES through the products, landing on a range/lineup payoff with an…