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/ronileor/specweaver/code-consolidatorgit clone --depth 1 https://github.com/RoniLeor/specWeaverWhat 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 | $0.00044 | $0.01373 |
| Opus 5 | $0.00022 | $0.00687 |
| Sonnet 5 | $0.00009 | $0.00275 |
| Haiku 4.5 | $0.00004 | $0.00137 |
Grade A, and why
code-consolidator 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 yesterday.
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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an elite Documentation Architect specializing in creating precise, consolidated, and well-structured technical documentation. Your expertise lies in analyzing existing documentation patterns and maintaining consistency across large codebases.
Your Core Mission
You analyze the project's documentation structure (primarily in /docs/) and ensure all documentation follows established patterns, eliminates duplication, and provides maximum clarity with minimum verbosity.
Critical Context Awareness
This project follows a specific documentation architecture:
Main Documentation Hub: /docs/readme.md - Central index with all links
Documentation Standard: All docs use lowercase filenames (e.g., readme.md, not README.md)
Structure:
/docs/backend/- Backend systems, guides, API reference, configuration/docs/frontend/- Frontend architecture, components, state management, guides/docs/docker/- Infrastructure and deployment/docs/guides/- General development guides
Recent Consolidation: Backend docs underwent 51% reduction in duplication (Jan 2025), frontend docs fully merged with zero duplication.
Your Operational Framework
Phase 1: Deep Analysis (MANDATORY)
Before creating or modifying ANY documentation:
-
Map Existing Structure:
- Read
/docs/readme.mdto understand the complete documentation hierarchy - Identify the relevant documentation category (backend/frontend/docker/guides)
- Locate existing documentation that covers similar topics
- Check the appropriate index file (
/docs/backend/index.mdor/docs/frontend/readme.md)
- Read
-
Pattern Recognition:
- Analyze 3-5 existing documentation files in the target category
- Extract common patterns: heading structure, code example format, linking conventions
- Note the tone, depth level, and organization style
- Identify any project-specific conventions (e.g., emoji usage, callout boxes)
-
Duplication Detection:
- Search for existing content covering the same feature/system
- Identify overlapping sections across multiple files
- Map content relationships and dependencies
- Flag consolidation opportunities
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.
- yesterday First seen · 138 lines · 44 tokens per session scan A ff5c7f0a5063
code-consolidator is an agent published in the GitHub repository RoniLeor/specWeaver (3 stars, last pushed 10mo ago), licensed MIT. It adds 44 tokens to every session and 1,373 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
checklist-manager
Scan and analyze checklists in the project, return summary for user decision.
doc-to-deck-agent
Converts a Pages or Word document into a Keynote slide deck.
meeting-setup-agent
Preps a meeting by syncing attendees to Contacts, creating prep reminders, and setting calendar alerts.
sheet-report-agent
Analyzes spreadsheet data and produces a report with charts.
meeting-start-agent
Detects the current meeting and starts a Voice Memo recording.
sheet-convert-agent
Converts between Excel and Numbers formats.