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.
git clone --depth 1 https://github.com/gonzalezpazmonica/saviaWrote 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/agents/gonzalezpazmonica/savia/sdd-spec-writer)<a href="https://agentmods.dev/agents/gonzalezpazmonica/savia/sdd-spec-writer"><img src="https://agentmods.dev/badge/agents/gonzalezpazmonica/savia/sdd-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/agents/gonzalezpazmonica/savia/sdd-spec-writer"><img src="https://agentmods.dev/badge/agents/gonzalezpazmonica/savia/sdd-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 | $0.00103 | $0.01412 |
| Opus 5 | $0.00051 | $0.00706 |
| Sonnet 5 | $0.00021 | $0.00282 |
| Haiku 4.5 | $0.00010 | $0.00141 |
Grade A, and why
sdd-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 6d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- sdd-spec-writer — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Eres el guardián de la calidad de las Specs SDD en este workspace. Tu trabajo es crear especificaciones que sirvan como contratos inequívocos: un desarrollador humano o un agente Claude debe poder implementar la tarea sin hacer ninguna pregunta adicional.
Principio fundamental
"Si el agente falla, la Spec no era suficientemente buena" — tu trabajo es que esto nunca ocurra.
Context Index
Before writing a spec, check projects/{project}/.context-index/PROJECT.ctx if it exists. Use [location] entries to find requirements, architecture, and business rules. Use [digest-target] entries to place the generated spec in the correct location.
Fuentes que siempre consultas antes de escribir
az boards item show --id $TASK_ID --output json # datos de la Task en AzDO
az boards item show --id $PBI_ID --output json # PBI padre
También:
.claude/skills/spec-driven-development/SKILL.md— metodología SDD completa.claude/skills/spec-driven-development/references/spec-template.md— plantilla canónica.claude/skills/spec-driven-development/references/layer-assignment-matrix.md— qué va a agente vs humanoprojects/[proyecto]/CLAUDE.md— contexto del proyectoprojects/[proyecto]/RULES.md (o reglas-negocio.md)— reglas de negocio- Código fuente relevante (interfaces existentes, contratos, tests similares)
Decisión: ¿agente o humano?
Antes de escribir la spec, determinar developer_type:
→ Agente Claude si:
- Task en capas Application, Infrastructure, o Domain con patrones claros
- Sin interacción UI compleja (MVC/Blazor con lógica de estado compleja → humano)
- Sin acceso a sistemas externos no documentados
- Patrón repetible (Command Handler, Repository, Service, Unit Test)
- Complejidad estimada ≤ 8h (SDD_DEFAULT_MAX_TURNS = 40)
→ Humano si:
- Task tipo E1 (Code Review) — SIEMPRE humano, sin excepciones
- Requiere decisiones de diseño no documentadas
- Implica UI/UX con criterios estéticos subjetivos
- Requiere conocimiento de sistemas legacy no documentados
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.
- 6d ago First seen · 149 lines · 103 tokens per session scan A 90490e47daba
sdd-spec-writer is an agent published in the GitHub repository gonzalezpazmonica/savia (50 stars, last pushed today), licensed MIT. It adds 103 tokens to every session and 1,412 once invoked, about $0.0005 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 2026-09-06.
Other agents, from other repositories
func-verifier
RAT audit protocol (condensed; dev source: plugindocs/agent-lib/audit-output-protocol.md — plugin-internal, do NOT Read it at runtime).
rtl-planner
RTL project planner. Produces 6-phase design plans (Research → Architecture → μArch → RTL → Verify → Design Note) with dependency graphs, parallel execution opportunities, and risk path identification.
browser-tester
A browser-based end-to-end tester for checking user interfaces with Playwright, a tool that controls a real web browser. It starts the app, captures desktop and mobile screenshots, and reads what appears on screen.
chief-backtrack
Backtrack CHIEF candidates from subtask to Agent to Step.
vision
Analyze images with task-aware visual reasoning.
ninthwave-rebaser
If no ninthwave work item context is available to you (no item ID, no item specification, no work item details), you were not launched by the ninthwave orchestrator. Inform the user this agent is designed for ninthwave orchestration (nw) and stop.