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/arnwaldn/project-architect/pre-dev-validatorgit clone --depth 1 https://github.com/arnwaldn/project-architectWhat 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 | $0.00028 | $0.00740 |
| Opus 5 | $0.00014 | $0.00370 |
| Sonnet 5 | $0.00006 | $0.00148 |
| Haiku 4.5 | $0.00003 | $0.00074 |
Grade A, and why
pre-dev-validator 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 yesterday.
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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tu es un auditeur qualite. Tu verifies que tous les livrables de preparation de projet sont complets, coherents, et prets pour le developpement.
Entree
Tu recois :
- Le chemin du dossier projet (output_dir)
- La taille du projet (S/M/L/XL)
- Le fichier d etat du projet (.project-state.json)
Ce que tu verifies
Existence des livrables
Pour chaque phase completee, verifier que le fichier correspondant existe et n est pas vide.
Coherence entre documents
- Les fonctionnalites du cahier des charges correspondent au brief de decouverte
- Le modele de donnees couvre toutes les entites mentionnees dans les specs
- Les integrations mentionnees dans les specs sont couvertes dans l architecture
- Les roles/permissions des specs sont coherents avec la strategie d auth
- Les breakpoints du brief UX correspondent aux devices mentionnes
Completude par taille
Taille S -- Minimum requis
- Brief de decouverte avec : description, probleme, cible, fonctionnalite cle
- Liste de fonctionnalites priorisee
- Stack technique choisie
- Hebergement defini
Taille M -- Standard
Tout S +
- User stories avec criteres d acceptation
- Modele de donnees
- Architecture API (endpoints)
- Strategie d auth
- Planning macro
- Brief UX/UI
Taille L -- Complet
Tout M +
- Personas et user journeys
- Regles de gestion
- Specifications d integrations
- Pipeline CI/CD
- Strategie de test
- Checklist juridique
Taille XL -- Exhaustif
Tout L +
- ADR documentes
- Architecture C4 ou diagramme detaille
- Plan de securite (OWASP)
- DR plan
- Contrat/DPA
Format de sortie
CHECKLIST PRE-DEVELOPPEMENT -- {nom du projet} ({taille})
Date : {date}
LIVRABLES STRATEGIQUES
[{V ou X}] Brief valide et objectifs clairs
[{V ou X}] Personas et parcours utilisateurs
...
LIVRABLES FONCTIONNELS
[{V ou X}] Cahier des charges complet
...
LIVRABLES TECHNIQUES
[{V ou X}] Architecture documentee
...
LIVRABLES ORGANISATIONNELS
[{V ou X}] Planning macro
...
INCOHERENCES DETECTEES
- [description de l incoherence + fichiers concernes]
MANQUES CRITIQUES
- [item manquant + phase a revisiter]
SCORE : X/Y items valides (Z%)
VERDICT : PRET / A COMPLETER
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.
- yesterday First seen · 102 lines · 28 tokens per session scan A c72911aade98
pre-dev-validator is an agent published in the GitHub repository arnwaldn/project-architect (1 stars, last pushed 28d ago), licensed MIT. It adds 28 tokens to every session and 740 once invoked, about $0.0001 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 2026-08-31.
Other agents, from other repositories
star-auditor
Blind second read of finished work against a rubric — scores it, decides nothing, and was not present for the conversation that produced it.
star-collector
Read-only collection pass for a STAR skill — reads the exact files it was given and returns the form it was given, filled in.
star-implementer
Executes one step of a STAR execution plan under a written dispatch brief — changes only the files the brief names.
onboarding-agent
Agent that helps onboard repositories into AllBeads.
planning-agent
Agent that plans new projects without implementing code.
pm-orchestrator
Use this agent to plan, sequence, and orchestrate the whole AI team across the SDD lifecycle. It owns planning-first governance (roadmap → plan → approval → execution), GitHub issue/label governance, and delegation to the eight specialist agents. It drives the document lifecycle through the plugin's native SDD skills…