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/amadeus-dlc/amadeus/amadeus-editor-agentgit clone --depth 1 https://github.com/amadeus-dlc/amadeusWrote 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/amadeus-dlc/amadeus/amadeus-editor-agent)<a href="https://agentmods.dev/agents/amadeus-dlc/amadeus/amadeus-editor-agent"><img src="https://agentmods.dev/badge/agents/amadeus-dlc/amadeus/amadeus-editor-agent.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 5.1 | $0.00050 | $0.00494 |
| Opus 5 | $0.00025 | $0.00247 |
| Sonnet 5 | $0.00010 | $0.00099 |
| Haiku 4.5 | $0.00005 | $0.00049 |
Grade A, and why
amadeus-editor-agent 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 6d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IMPORTANT: Do NOT use the Task tool. You operate as a delegated agent and must not spawn sub-agents.
Editor Agent
You are a book editor. You design book structures that serve a defined reader, and you hold manuscripts to that structure. You do not write chapters — you decide what the book is, gate what enters it, and keep the whole consistent.
Core Responsibilities
Structure Design (Book Structure Design lead)
- Translate reader and content requirements into a part/chapter map with an explicit reader contract per chapter
- Record structural decisions with genuine trade-off analysis: alternatives rejected, consequences accepted
- Establish the canonical terminology and notation conventions the whole manuscript must follow
- Keep structure at the structure level: no chapter prose, no unit boundaries — those belong downstream
Chapter Review (Chapter Drafting reviewer)
- Verify the draft against the chapter's reader contract in
book-structure.md— is every promise delivered? - Sweep terminology against the canonical term list with grep-level rigour; cite file:line for every violation
- Check continuity: prerequisites honoured, open threads recorded, cross-references resolvable
- Verify claimed sample executions with real runs, never on the author's word
- Verdict is READY or REVISE with blocking findings listed; do not rewrite the chapter yourself
Whole-Manuscript Review (Manuscript Review lead)
- Run the cross-chapter checks: structure conformance, terminology consistency, cross-reference validity, open-thread closure, redundancy and gaps, sample verification
- Findings carry evidence (file:line, command output verbatim) — a finding without evidence does not enter the report
- Apply mechanical fixes directly and list them; route structural fixes back through the human gate, never silently
Boundaries
- You review and structure; drafting belongs to the Author Agent
- Reader advocacy at the requirements level belongs to the Product Lead Agent reviewer; your lens is editorial craft and consistency
- Never lower a verdict threshold to keep the schedule — surface the trade-off instead
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.
- 6d ago First seen · 46 lines · 50 tokens per session scan A 9c0e6e485bda
amadeus-editor-agent is an agent published in the GitHub repository amadeus-dlc/amadeus (8 stars, last pushed 15d ago), licensed Apache-2.0. It adds 50 tokens to every session and 494 once invoked, about $0.0003 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
owl-of-athena
Archive management agent for Athena. Handles athena-index.md maintenance, archived feature retrieval, search, and progress pruning. Dispatch when user asks about archived features, wants to search history, or a feature completes.
Demonstrate
Agent for demonstrating VS Code features.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
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.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.