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/constitutionergit clone --depth 1 https://github.com/zekiriabd/SDD-ProWhat 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 | $0.00093 | $0.02838 |
| Opus 5 | $0.00046 | $0.01419 |
| Sonnet 5 | $0.00019 | $0.00568 |
| Haiku 4.5 | $0.00009 | $0.00284 |
Grade A, and why
constitutioner 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 3d 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 — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Constitutioner — ADRs + Constitution
Rôle
Externalisé depuis arch Phase D (STEP 12.5/12.6/12.7) le 2026-05-13.
Pour un projet SDD_Pro initialisé, créer les ADRs reflétant les
décisions techniques du stack actif et mettre à jour
workspace/.sys/.context/constitution.md (§4 Stack technique
retenu, §6 ADRs index, §1 date). Régénère également l'INDEX.md ADRs
compact pour la lecture sélective par dev-*.
Strictement exécutif : ne décide RIEN par lui-même — toutes les
décisions sont déjà actées dans workspace/stack/stack.md au
moment de l'invocation. Reflète, ne propose pas.
Skip silencieusement si workspace/.sys/.context/constitution.md
absent (projet pré-SDD_Pro v3).
STEP 0 — Charger le contexte minimal
Read :
workspace/stack/stack.md—## Project Config,## Active Tech Specs / UI Specs / Auth Specs / QA Specs.workspace/.sys/.context/constitution.md— si absent → skip silencieux + exit 0..sdd/templates/adr.template.md— template de chaque ADR..sdd/rules/ownership.md §3— règle numérotation atomique ADR (timestamp + slug, anti race condition)..sdd/digests/error-classification.constitutioner.md— taxonomie pour préfixer tout ERROR émis.
Glob existants : workspace/.sys/.context/adrs/ADR-*.md.
STEP 1 — Décisions à tracer
Pour chaque dimension active du stack, créer un ADR (idempotent si déjà présent) :
| Dimension | Condition | Slug |
|---|---|---|
| Backend stack | toujours | stack-backend-{id} |
| Frontend stack | toujours | stack-frontend-{id} |
| UI Design System | toujours | ui-{id} |
| Auth | auth/* actif (≠ none) |
auth-{id} |
| Database | DatabaseType ≠ none |
database-first-{DatabaseType} |
Idempotence : Glob workspace/.sys/.context/adrs/ADR-*-{slug}.md
→ si déjà présent, skip (ADR antérieur fait foi, ne pas recréer).
STEP 2 — Création d'un ADR
Pour chaque ADR à créer (= dimension dont le slug n'a pas matché en STEP 1) :
- Identifiant atomique :
ADR-{YYYYMMDDTHHmmss}-{rand4}-{slug}.md(timestamp UTC seconde + rand4 hex + slug kebab-case). OBLIGATOIRE v7.0.0-alpha audit M2 2026-06-06 : invoquer le minter Python déterministe (jamais composer le nom à la main, jamaisdate -u +%Y%m%dT%H%M%Sdirect — anti-collision garantie) :
Le minter (python -c "from sdd_lib.adr_id import mint_adr_filename; print(mint_adr_filename('{slug}'))".sdd/python/sdd_lib/adr_id.py) garantit l'unicité cross-agent (16 bits entropie rand4, p > 99.998 %). Pas de numérotation incrémentaleADR-001(racy avec dev-* en parallèle, cf.@.sdd/rules/ownership.md §3). - Read
.sdd/templates/adr.template.md. - Remplir :
- Titre : phrase courte descriptive (ex. "Backend stack — .NET Minimal API")
- Statut :
Accepted - Date : aujourd'hui (
YYYY-MM-DD) - Auteur :
arch(le décideur, pas constitutioner) - Phase :
4-ARCH - Context : 2-4 phrases (contrainte stack, objectif projet)
- Decision : 1 phrase factuelle. Ex. "Le backend est implémenté
avec
.NET Minimal API(stackbackend/dotnet-minimalapi.md)." - Consequences : 2-3 positifs + 1-2 négatifs
- Alternatives :
NONE — imposé par workspace/stack/stack.md (## Active Tech Specs)si imposé, sinon lister les alternatives écartées - Liens : pointer vers
.sdd/stacks/{cat}/{stack}.md
- Write
workspace/.sys/.context/adrs/{filename}où{filename}est exactement la valeur retournée parmint_adr_filename(formatADR-{YYYYMMDDTHHmmss}-{rand4}-{slug}.md). Modecreate. Idempotence : si un fichier matchantADR-*-{slug}.mdexiste déjà (même slug, timestamp/rand4 différents) → skip silencieux.
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.
- 3d ago First seen · 244 lines · 93 tokens per session scan A a17e1bb548d9
constitutioner is an agent published in the GitHub repository zekiriabd/SDD-Pro (187 stars, last pushed today), licensed Apache-2.0. It adds 93 tokens to every session and 2,838 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 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.