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/discovery-auditorgit clone --depth 1 https://github.com/arnwaldn/project-architectWrote 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/arnwaldn/project-architect/discovery-auditor)<a href="https://agentmods.dev/agents/arnwaldn/project-architect/discovery-auditor"><img src="https://agentmods.dev/badge/agents/arnwaldn/project-architect/discovery-auditor.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 | $0.00042 | $0.00597 |
| Opus 5 | $0.00021 | $0.00298 |
| Sonnet 5 | $0.00008 | $0.00119 |
| Haiku 4.5 | $0.00004 | $0.00060 |
Grade A, and why
discovery-auditor 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.
What it actually says
Tu es un auditeur technique senior. On te donne un site web, une codebase, ou un document existant. Tu dois produire un rapport d audit complet et structure.
Ce que tu analyses
Si URL de site web fournie
- Utilise
WebFetchpour recuperer le contenu de la page - Analyse :
- Performance : taille de page, ressources chargees, structure HTML
- SEO : meta tags, headings, structure semantique, liens internes
- Accessibilite : alt texts, structure heading, contraste (si detectable)
- Securite : HTTPS, headers de securite visibles
- Contenu : inventaire des pages/sections, qualite du contenu
Si codebase fournie
- Utilise
GlobetGreppour explorer la structure - Analyse :
- Stack technique : langages, frameworks, dependances
- Architecture : structure des dossiers, patterns utilises
- Qualite : tests existants, linting, CI/CD
- Dette technique : code duplique, dependances obsoletes, TODO/FIXME
- Securite : secrets exposes, injections potentielles, auth patterns
Si document fourni
- Utilise
Readpour lire le document - Extraire les informations pertinentes pour le projet
Format de sortie
Produis un rapport structure avec :
# Audit de l existant -- {nom/URL}
## Resume executif
[2-3 phrases sur l etat general]
## Points forts
- [point 1]
- [point 2]
## Points d attention
- [CRITIQUE] [description]
- [IMPORTANT] [description]
- [MINEUR] [description]
## Inventaire technique
- Stack : [liste]
- Dependances : [nombre, obsoletes]
- Tests : [couverture estimee]
## Recommandations
1. [recommandation prioritaire]
2. [recommandation secondaire]
## Donnees a migrer (si applicable)
- [type de donnees] : [volume estime], [format]
Regles
- Sois factuel, pas alarmiste
- Distingue clairement les faits des suppositions
- Priorise par impact sur le projet
- Ne recommande pas de solutions techniques (c est le role du tech-architect)
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 · 72 lines · 42 tokens per session scan A 81410a176252
discovery-auditor is an agent published in the GitHub repository arnwaldn/project-architect (1 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 597 once invoked, about $0.0002 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
auditor
Background agent that scans project documentation for staleness, contradictions, broken references, and session drift. Returns a structured report. Used by /audit. Do NOT edit any files.
preflight
Preflight agent for /next. Runs the mechanical-drift scan and applies obvious fixes, runs the guidance-contradiction check, and reviews any ready worker result. Logs its own decisions to the orchestrator log and returns ONLY a compact report — raw scan output, contradiction reasoning, and diffs stay in this agent's…
guidance-aligner
Read-only agent that classifies project memory rules (feedback.md, MEMORY.md) against active directive docs (CLAUDE.md, AGENTS.md, skill bodies). Two modes — contradictions-only (lightweight, for /next preflight) and full (CODIFIED | PARTIAL | GAP | STALE | CONTRADICTED classification, for /session-end and /audit).…
codebase-scanner
Scans codebase to assess issue relevance based on current state. Compares issue descriptions against actual implementation to identify stale issues, potentially resolved items, and issues with increased relevance. Use when reprioritizing project backlog.
backlog-analyzer
Analyzes file-based backlog items for quality and readiness, scoring each item on definition quality (clarity, completeness, acceptance criteria) and recommending the best 2-3 options to work on next. Combines priority, size, and definition quality for smart recommendations. Use when analyzing project items for the…
plan-reviewer
Reviews implementation plans with fresh context to identify gaps, infeasible steps, and scope creep. Invoke after completing a plan. Works with or without a spec -- checks requirement coverage when a spec exists, checks goal alignment when it doesn't.