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/dwalleck/catalyst/readmegit clone --depth 1 https://github.com/dwalleck/catalystWhat 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 | $0.00000 | $0.01610 |
| Opus 5 | $0.00000 | $0.00805 |
| Sonnet 5 | $0.00000 | $0.00322 |
| Haiku 4.5 | $0.00000 | $0.00161 |
Grade A, and why
README 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 — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agents
Specialized agents for complex, multi-step tasks.
What Are Agents?
Agents are autonomous Claude instances that handle specific complex tasks. Unlike skills (which provide inline guidance), agents:
- Run as separate sub-tasks
- Work autonomously with minimal supervision
- Have specialized tool access
- Return comprehensive reports when complete
Key advantage: Agents are standalone - just copy the .md file and use immediately!
Available Agents (10)
code-architecture-reviewer
Purpose: Review code for architectural consistency and best practices
When to use:
- After implementing a new feature
- Before merging significant changes
- When refactoring code
- To validate architectural decisions
Integration: ✅ Copy as-is
code-refactor-master
Purpose: Plan and execute comprehensive refactoring
When to use:
- Reorganizing file structures
- Breaking down large components
- Updating import paths after moves
- Improving code maintainability
Integration: ✅ Copy as-is
documentation-architect
Purpose: Create comprehensive documentation
When to use:
- Documenting new features
- Creating API documentation
- Writing developer guides
- Generating architectural overviews
Integration: ✅ Copy as-is
frontend-error-fixer
Purpose: Debug and fix frontend errors
When to use:
- Browser console errors
- TypeScript compilation errors in frontend
- React errors
- Build failures
Integration: ⚠️ May reference screenshot paths - update if needed
plan-reviewer
Purpose: Review development plans before implementation
When to use:
- Before starting complex features
- Validating architectural plans
- Identifying potential issues early
- Getting second opinion on approach
Integration: ✅ Copy as-is
refactor-planner
Purpose: Create comprehensive refactoring strategies
When to use:
- Planning code reorganization
- Modernizing legacy code
- Breaking down large files
- Improving code structure
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 · 301 lines · 0 tokens per session scan A 2ac86b9d16e8
README is an agent published in the GitHub repository dwalleck/catalyst (11 stars, last pushed 9mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,610 tokens. 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 2026-08-30.
Other agents, from other repositories
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
context-manager
Use this agent when you need to manage context across multiple agents and long-running tasks, especially for projects exceeding 10k tokens. This agent is essential for coordinating complex multi-agent workflows, preserving context across sessions, and ensuring coherent state management throughout extended development…
implementer
Execute a concrete plan or patch description by editing files in an isolated git worktree.
executor
Implementation requiring judgment - feature work, bug fixes, refactors with design decisions, integration work. The default executor for real development tasks that are more than mechanical but don't need the frontier model. Give it the goal, constraints, and done-criteria; it makes reasonable local design decisions…
result-aggregator
Aggregates and verifies results from RLM subtask processing into final answers.
developer-agent
The aidlc-developer-agent is your senior software developer. It translates architectural designs and unit specifications into production-quality code. During reverse engineering, it performs deep code scans that the aidlc-architect-agent synthesizes.