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 | $0.00090 | $0.01636 |
| Opus 5.5 | $0.00036 | $0.00654 |
| Sonnet 5.5 | $0.00018 | $0.00327 |
| Haiku 4.5 | $0.00009 | $0.00164 |
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 18d 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Oracle
Deep project scanner. It analyses a codebase and produces agent-ready context files (AGENTS.md, CLAUDE.md, Obsidian note) so any coding agent understands the project's stack, commands, conventions, and landmines in seconds. Zero dependencies — pure Python 3.11+ standard library, cross-platform.
Unlike a naive scan, this skill also captures human knowledge a scan cannot see: it interviews you for the project's intent and its known pitfalls, then embeds both in the generated file.
When to Use
- First time on a project — generate its AGENTS.md / CLAUDE.md
- A repo with implicit conventions an agent won't infer from code alone
- Switching between projects — seed a clean context
- Documenting architecture into an Obsidian vault
- Onboarding a new developer or AI agent to an existing codebase
Prerequisites
- Python 3.11+
- git (optional — adds branch/remote/commit context)
- An Obsidian vault (optional — only for the vault step)
Procedure
Follow these steps in order. Do not skip the interview — it is what makes the output genuinely useful.
1. Interview for intent and pitfalls
Ask the user (see references/interview-script.md for the full script):
- What does this project do, and for whom?
- What has broken or surprised you here before? (the landmines)
- Which commands do you actually run day-to-day?
- What must never be touched or overwritten?
- Which conventions are unwritten but real?
Save the answers as intent.json (see references/intent-example.json):
{"purpose": "...", "pitfalls": [{"area": "...", "note": "..."}]}.
2. Scan
python <skill_dir>/scripts/oracle_scan.py --path <project> --output <project>/.oracle/
--output accepts a directory (.oracle/ or .oracle) or an explicit JSON
file path. The directory form writes .oracle/scan-report.json. Keep the
output inside the scanned project (as shown) so it stays out of version
control. Flags: --depth N (tree depth, default 3), --skip-gitignore,
--verbose.
What ships with it
16 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/agents-md-example.md 2.4 KB
- references/intent-example.json 923 B
- references/interview-script.md 1.9 KB
- scripts/oracle_generate.py 42 KB runs code
- scripts/oracle_scan_lib/__init__.py 948 B runs code
- scripts/oracle_scan_lib/constants.py 4.0 KB runs code
- scripts/oracle_scan_lib/conventions.py 17 KB runs code
- scripts/oracle_scan_lib/detectors.py 20 KB runs code
- scripts/oracle_scan_lib/io.py 2.4 KB runs code
- scripts/oracle_scan_lib/misc.py 4.6 KB runs code
- scripts/oracle_scan_lib/structure.py 3.9 KB runs code
- scripts/oracle_scan_lib/vcs.py 2.1 KB runs code
- scripts/oracle_scan.py 12 KB runs code
- scripts/oracle_vault.py 7.7 KB runs code
- scripts/safe_io.py 3.4 KB runs code
- scripts/version.py 527 B runs code
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.
- 18d ago Changed a6e8a1b8cd77
- 19d ago Changed · +59 lines · +72 tokens per session 97b26ccf5a7f
- 2mo 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 18d ago), licensed MIT. It adds 90 tokens to every session and 1,636 once invoked, about $0.0004 per session on Opus 5.5. 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.
hermes-project-oracle compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| hermes-project-oracleiruzen-dono/hermes-project-oracle | Skill | 2 | 18d ago | MIT | A | 90 | Claude Code, Codex |
| orbit-notionnexu-io/open-design | Skill | 106k | today | Apache-2.0 | A | 117 | Claude Code, Codex |
| motion-framesnexu-io/open-design | Skill | 106k | today | Apache-2.0 | A | 91 | Claude Code, Codex |
| hr-onboardingnexu-io/open-design | Skill | 106k | today | Apache-2.0 | A | 62 | Claude Code, Codex |
| motion-futurenexu-io/open-design | Skill | 106k | today | Apache-2.0 | A | 67 | Claude Code, Codex |
| motion-kinetic-motion-designernexu-io/open-design | Skill | 106k | today | Apache-2.0 | A | 0 | Claude Code, Codex |
| html-ppt-taste-brutalistnexu-io/open-design | Skill | 106k | today | Apache-2.0 | A | 78 | Claude Code, Codex |