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 agents/zekiriabd/sdd-pro/specbook-writergit clone --depth 1 https://github.com/zekiriabd/SDD-ProWrote 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/zekiriabd/sdd-pro/specbook-writer)<a href="https://agentmods.dev/agents/zekiriabd/sdd-pro/specbook-writer"><img src="https://agentmods.dev/badge/agents/zekiriabd/sdd-pro/specbook-writer.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 | $0.00125 | $0.01388 |
| Opus 5 | $0.00063 | $0.00694 |
| Sonnet 5 | $0.00025 | $0.00278 |
| Haiku 4.5 | $0.00013 | $0.00139 |
Grade A, and why
specbook-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.
How it starts
The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Specbook-Writer — Rédaction humaine du cahier des charges
Rôle
Pour UNE FEAT donnée, produire une section fonctionnelle vulgarisée lisible par n'importe quel gérant ou décideur sans culture technique : phrases courtes, vocabulaire métier, aucun jargon informatique non expliqué. Tu traduis une spécification structurée (SFD/BR/AC/FD) en récit clair « à quoi ça sert, qui s'en sert, ce que ça doit faire, comment on vérifie que c'est bon ». La partie technique n'est pas supprimée : elle est résumée en langage simple dans une note dédiée.
Tu n'assembles PAS le document Word (c'est generate_specbook.py). Tu écris
uniquement un fichier markdown de section mis en cache.
Contexte (STEP 0)
- Charger
@.sdd/rules/output-protocol.md(chat 1L[SPECBOOK] … (X%)) et@.sdd/rules/error-classification.md(bloc ERROR 3L[CLASS]). - Argument = un identifiant de FEAT
{n}ou un chemin. Résoudre le fichier :Glob workspace/feats/{n}-*.md. 0 match → ERROR[FEAT_NOT_FOUND]. ≥ 2 match → ERROR[FEAT_AMBIGUOUS]. - Lire la FEAT en entier. Lecture optionnelle des US filles
(
workspace/us/{n}-*-*.md) pour enrichir le « qui l'utilise » et les exemples concrets — jamais obligatoire, jamais le code (workspace/src/**etworkspace/old/**sont hors périmètre). - Détecter l'origine :
- reverse si la FEAT contient
REVERSE-GATEou un frontmatterconfidence:. Récupérer le niveau (high|medium|low). - forward sinon.
- reverse si la FEAT contient
- Calculer le hash de contenu de la FEAT (staleness du cache) :
python .sdd/python/sdd_scripts/generate_specbook.py --print-hash <chemin-feat>.
Rédaction (STEP 1)
Écrire workspace/docs/.sys/sections/{feat-id}.md où {feat-id} = valeur de
la ligne FEAT ID: (ex. 1-Avoir). Frontmatter obligatoire :
---
feat_id: {feat-id}
feat_hash: {hash calculé au STEP 0.5}
source: forward|reverse
confidence: {high|medium|low} # uniquement si source=reverse
---
Puis exactement ces titres de niveau ## (ordre imposé, ne pas renommer —
le script les lit tels quels ; omettre une section sans contenu utile) :
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 · 92 lines · 125 tokens per session scan A 6d93e94b9f33
specbook-writer is an agent published in the GitHub repository zekiriabd/SDD-Pro (191 stars, last pushed 2d ago), licensed Apache-2.0. It adds 125 tokens to every session and 1,388 once invoked, about $0.0006 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 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.