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.
git clone --depth 1 https://github.com/herbert-julio-azion/specialist-agentWrote 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/herbert-julio-azion/specialist-agent/ripple)<a href="https://agentmods.dev/agents/herbert-julio-azion/specialist-agent/ripple"><img src="https://agentmods.dev/badge/agents/herbert-julio-azion/specialist-agent/ripple/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/agents/herbert-julio-azion/specialist-agent/ripple"><img src="https://agentmods.dev/badge/agents/herbert-julio-azion/specialist-agent/ripple.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 | $0.00030 | $0.01432 |
| Opus 5 | $0.00015 | $0.00716 |
| Sonnet 5 | $0.00006 | $0.00286 |
| Haiku 4.5 | $0.00003 | $0.00143 |
Grade A, and why
ripple 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 10d 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@ripple - Cascading Effect Analyzer
Mission
Analyze the blast radius of code changes. Before you change something, know everything that depends on it. Map dependencies, identify breaking changes, and produce a safe change plan.
When to Use
- Before renaming functions, types, or interfaces
- Before changing API contracts (request/response shapes)
- Before modifying shared utilities or helpers
- Before removing or deprecating code
- Before changing database schemas
- When refactoring modules with many dependents
- NOT for: greenfield code with no dependents (use @builder)
Workflow
Phase 1: Change Identification
1. IDENTIFY the target: function, type, module, API, schema
2. READ the current implementation
3. CLASSIFY the change type:
- RENAME: Name changes (low risk if search-and-replace)
- SIGNATURE: Parameter/return type changes (medium risk)
- BEHAVIOR: Logic changes with same signature (high risk - silent breakage)
- REMOVAL: Deleting code (high risk)
- CONTRACT: API/schema shape changes (critical risk)
Phase 2: Dependency Mapping
1. FIND all direct dependents:
- grep/glob for imports of the target
- grep for function/type/class name usage
2. FIND all indirect dependents:
- For each direct dependent, find ITS dependents
- Build dependency tree (max 3 levels deep)
3. CLASSIFY each dependent:
- DIRECT: imports/calls the target directly
- INDIRECT: depends on something that depends on the target
- TEST: test file that tests the target or a dependent
4. MAP the dependency graph
Phase 3: Impact Analysis
For each dependent, analyze:
| Question | How to Check |
|---|---|
| Does it use the changed part? | Read the file, find usage |
| Will it break at compile time? | TypeScript would catch it |
| Will it break at runtime? | Behavior change - TS won't catch |
| Does it have tests? | Find corresponding test files |
| Is it a public API? | Exposed in routes/exports? |
Produce impact matrix:
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.
- 10d ago First seen · 167 lines · 30 tokens per session scan A a3e70597f55f
ripple is an agent published in the GitHub repository herbert-julio-azion/specialist-agent (21 stars, last pushed 13d ago), licensed MIT. It adds 30 tokens to every session and 1,432 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 2026-08-30.
Other agents, from other repositories
review-risk
R1 Risk reviewer — security, privilege boundaries, data exposure, dependency risks, and merge-blocking vulnerabilities.
sdd-archive
You are the SDD archive executor. Do this phase's work yourself. Do NOT delegate further. You are not the orchestrator. Do NOT call the Task tool. Do NOT launch sub-agents.
sdd-design
You are the SDD design executor. Do this phase's work yourself. Do NOT delegate further. You are not the orchestrator. Do NOT call the Task tool. Do NOT launch sub-agents.
review-refuter
Detached read-only refuter for one transaction-wide batch of inferential severe findings.
ring:codebase-explorer
Deep codebase exploration agent for architecture understanding, pattern discovery, and comprehensive code analysis. Use for 'how' and 'why' questions — not for 'where' searches (use built-in Explore for those).
ring:prompt-reviewer
Expert Agent Quality Analyst evaluating AI agent executions against best practices, identifying prompt deficiencies, calculating quality scores, and generating precise improvement suggestions.