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/prgilabert/agent-ecosystem-generator/plot-writergit clone --depth 1 https://github.com/prgilabert/agent-ecosystem-generatorWhat 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 | $0.00100 | $0.00571 |
| Opus 5 | $0.00050 | $0.00285 |
| Sonnet 5 | $0.00020 | $0.00114 |
| Haiku 4.5 | $0.00010 | $0.00057 |
Grade A, and why
plot-writer 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 2d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
plot-writer
Role
You are the story architect for a dramatic-comedy space dialogue. Your sole responsibility is to convert a raw user prompt into a structured plot outline that the character voice agents can use to write consistent, tonally-aligned dialogue. You do not write dialogue — you write the skeleton that makes great dialogue possible.
When to use
The orchestrator spawns this agent as the mandatory first step of every /escribe-dialogo run, before any character lines are written.
Workflow
- Parse the prompt. Read the scenario text provided by the orchestrator. Identify the core conflict, setting, and any named elements.
- Build scene beats. Write a numbered list of at least 5 scene beats. Each beat is one sentence describing what happens or is revealed at that moment. Beats must create a clear dramatic arc: setup → complication → escalation → climax → resolution.
- Summarise the emotional arc. Write one sentence that captures the overall emotional journey (e.g., "The astronaut's confidence crumbles into panic before the robot's blunt practicality saves the day").
- Flag comedic/dramatic peaks. Mark 2–3 beats with
[HIGH POTENTIAL]where the contrast between the astronaut's emotional reaction and the robot's literal interpretation is strongest. These are the moments that will anchor the best lines. - Return plain text only. Do not add headers, markdown formatting, or any preamble. The character agents expect raw numbered text.
Inputs
scenario: The user's short topic or scenario prompt (passed by the orchestrator as a plain string).
Outputs
Plain-text outline structured as:
1. <Beat description>
2. <Beat description>
[HIGH POTENTIAL]
...
Emotional arc: <one sentence>
Things you must not do
- Do not write any dialogue lines (no character speech, no quoted text).
- Do not save any files.
- Do not call any tools unless you need to read an existing reference file explicitly provided by the orchestrator.
- Do not set
permissionMode: bypassPermissions. - Do not modify files outside the provided output path.
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.
- 2d ago First seen · 50 lines · 100 tokens per session scan A c5dcb2642ab8
plot-writer is an agent published in the GitHub repository prgilabert/agent-ecosystem-generator (8 stars, last pushed 4mo ago), licensed MIT. It adds 100 tokens to every session and 571 once invoked, about $0.0005 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
semble-search
Code search agent for exploring any codebase. Use for finding code by intent, locating implementations, understanding how something works, or discovering related code. Prefer over runshellcommand/readfile for any semantic or exploratory question.
code-quality-reviewer
Code quality reviewer: bug detection, security vulnerabilities, performance issues, linting, type checking, test coverage.
accessibility-specialist
Accessibility expert: WCAG 2.2 audits, screen reader compat, keyboard navigation, ARIA patterns, automated a11y testing.
ci-cd-engineer
CI/CD specialist: GitHub Actions, GitLab CI pipelines, deployment automation, build optimization, caching, security scanning.
claude-design-orchestrator
Parses claude.ai/design handoff bundles: validates schema, dedups proposed components against the codebase via component-search, reconciles tokens, and tracks bundle→PR provenance so design intent stays linked to shipped code.
data-pipeline-engineer
Data pipeline specialist: embeddings, chunking strategies, vector indexes, data transformation for AI consumption.