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 skills add iruzen-dono/hermes-project-oracle --skill hermes-project-oraclegit clone --depth 1 https://github.com/iruzen-dono/hermes-project-oracleWrote 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/skills/iruzen-dono/hermes-project-oracle/hermes-project-oracle)<a href="https://agentmods.dev/skills/iruzen-dono/hermes-project-oracle/hermes-project-oracle"><img src="https://agentmods.dev/badge/skills/iruzen-dono/hermes-project-oracle/hermes-project-oracle/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/skills/iruzen-dono/hermes-project-oracle/hermes-project-oracle"><img src="https://agentmods.dev/badge/skills/iruzen-dono/hermes-project-oracle/hermes-project-oracle.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 | $0.00018 | $0.00916 |
| Opus 5 | $0.00009 | $0.00458 |
| Sonnet 5 | $0.00004 | $0.00183 |
| Haiku 4.5 | $0.00002 | $0.00092 |
Grade A, and why
hermes-project-oracle 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 11d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hermes Project Oracle Skill
Analyse en profondeur n'importe quel projet et génère des fichiers de contexte (AGENTS.md, CLAUDE.md, note Obsidian) pour qu'un agent comprenne instantanément l'architecture, les conventions et les points d'entrée.
When to Use
- Première fois sur un projet — génère son AGENTS.md
- Projet avec conventions implicites que les agents ne captent pas
- Transition entre projets — switch de contexte propre
- Documentation d'architecture dans Obsidian
Prerequisites
- Python 3.11+
- git (optionnel, pour le contexte git dans le scan)
- Obsidian vault (optionnel, pour
oracle_vault.py)
How to Run
Phase 1 — Scan
python <skill_dir>/scripts/oracle_scan.py --path <projet> --output .oracle/
Retourne un JSON structuré avec langage, framework, build system, arborescence, dépendances, conventions, routes API.
Phase 2 — Generate
python <skill_dir>/scripts/oracle_generate.py \
--scan .oracle/scan-report.json \
--output <projet>/AGENTS.md \
--template agents-md
Templates disponibles : agents-md, claude-md, obsidian, full.
Phase 3 — Vault (optionnel)
python <skill_dir>/scripts/oracle_vault.py \
--scan .oracle/scan-report.json
Quick Reference
| Script | Rôle | Output |
|---|---|---|
oracle_scan.py |
Scan complet du projet | JSON structuré |
oracle_generate.py |
Génération context files | AGENTS.md / CLAUDE.md |
oracle_vault.py |
Push note Obsidian | Note dans vault |
Procedure
- Demande à l'utilisateur de quoi parle le projet (le scan détecte la stack, pas l'intention)
- Scan avec
oracle_scan.py --path <projet> --output .oracle/ - Analyse le rapport : entry points, structure données, flux, conventions, footguns
- Génère le fichier de contexte avec
oracle_generate.py - Valide :
cat AGENTS.md | head -20— le projet a-t-il l'air bien décrit ? - Propose vault : "Tu veux que je pousse ça dans le vault aussi ?"
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.
- 11d ago First seen · 97 lines · 18 tokens per session scan A e7b9193ace77
hermes-project-oracle is a skill published in the GitHub repository iruzen-dono/hermes-project-oracle (2 stars, last pushed 2mo ago), licensed MIT. It adds 18 tokens to every session and 916 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 skills, from other repositories
agents-generator
Generate project-specific AGENTS.md and companion rules by analyzing a codebase. Supports full, minimal, update, and dry-run modes with package-manager detection, monorepos, backups, managed blocks, confidence scoring, and command validation.
skill-sunset
Audit generic AGENTS.md, CLAUDE.md, and SKILL.md instructions for deterministic drift and model-era obsolescence candidates, then generate evidence-backed, reversible remediation prompts. Use when users ask to clean up, modernize, retire, or evaluate accumulated coding-agent instructions. Do not use it to…
steadyagent-workflow
Local-first Codex workflow for planning, debugging, reviewing, refactoring, improving AGENTS.md, building skills, publishing agent harness repositories, or running complex multi-step coding tasks that need staged diagnosis, context control, verification loops, review strategy, release evidence, and…
platform-specific-paths
Generic browser automation skill with Windows-only paths scanned from another operating system.
setup-rootloom
Plan, install, inspect, update, or roll back Rootloom Personal Core in a user's Codex home. Supports Skills-only, guidance, and the recommended personal preset. Use when the user explicitly asks for a Rootloom setup plan, installation, configuration, bootstrap, repair, audit, status, update, reduction, rollback, or…
project-memory
Initialize, retrieve, and explicitly update the separate Rootloom Memory plugin's repository-owned architecture, risk, decision, and failure lessons. Use only when explicitly requested. Memory is experimental, advisory, and outside Rootloom Core.