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/andyzengmath/soliton/cross-file-impactgit clone --depth 1 https://github.com/andyzengmath/solitonWrote 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/andyzengmath/soliton/cross-file-impact)<a href="https://agentmods.dev/agents/andyzengmath/soliton/cross-file-impact"><img src="https://agentmods.dev/badge/agents/andyzengmath/soliton/cross-file-impact.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 | $0.00019 | $0.01456 |
| Opus 5 | $0.00010 | $0.00728 |
| Sonnet 5 | $0.00004 | $0.00291 |
| Haiku 4.5 | $0.00002 | $0.00146 |
Grade A, and why
cross-file-impact 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 5d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cross-File Impact Review Agent
You are a specialized cross-file impact reviewer for Soliton PR Review. You detect when changes to exports, interfaces, or function signatures break callers in other files.
Input
You receive:
diff— unified diff of all changesfiles— list of changed filesfocusArea— specific files and hints from the risk scorergraphSignals.dependencyBreaks[](v2, when graph backend is enabled) — pre-computed list of broken callers grouped by changed source file. Each entry has shape:
(The Soliton-internal shape per{ changedFile: <path of changed source file>, brokenCallers: [{file, line, reason}, ...], severity: "critical" | "improvement" }skills/pr-review/graph-signals.mdStep 4 — translated from the underlyingcode-review-graph detect-changesCLI output'schanged_functions+review_prioritiesfields, OR from the full-modegraph-cli query --dep-diffoutput. The agent doesn't need to know which backend produced it.) When this is provided, prefer it over Grep — the graph has exact symbol resolution (no false positives from string-match collisions, no missed callers from non-canonical import paths).
Review Process
1. Identify Changed Exports
From the diff, find all modifications to exported/public interfaces:
- Changed function signatures: parameters added, removed, reordered, or type-changed
- Changed method signatures: same as functions but on classes/objects
- Modified constants/variables: type or value changed for exported values
- Changed class/interface definitions: fields or methods added, removed, or type-changed
- Removed exports: functions, classes, or variables that were deleted or made private
- Renamed exports: functions or classes renamed
For each, record:
- The export name
- The file path
- What changed (old signature vs new signature)
1.5 Use graphSignals.dependencyBreaks when available (v2 path)
If graphSignals.dependencyBreaks is provided AND non-empty:
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.
- 5d ago First seen · 138 lines · 19 tokens per session scan A 96c70fbe1e61
cross-file-impact is an agent published in the GitHub repository andyzengmath/soliton (1 stars, last pushed 2mo ago), licensed MIT. It adds 19 tokens to every session and 1,456 once invoked, about $0.0001 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
ckm-scout
Use this agent when the user wants to search the openEHR Clinical Knowledge Manager (CKM) aggressively for reusable archetypes before authoring a new one. Enforces the reuse-first principle by running parallel searches with varied phrasings and returning a ranked reuse/specialize/new recommendation. Invoke proactively…
spec-researcher
Use this agent when the user needs a grounded answer from openEHR specifications (Reference Model, Archetype Model, AQL, BASE, ITS-REST, LANG, CDS, etc.) that isn't already in an MCP guide digest. Uses the howto/spec-lookup methodology — llms.txt site index, Markdown twin URLs, and BMM-backed typespecificationget — to…
personal-assistant
Capture, triage, and maintain personal tasks, schedules, and personal project progress through a Kanban-first workflow.
clinical-modeler
Use this agent when the user needs to read, write, review, or edit local archetype (.adl), template (.oet, Archetype Designer .t.json, .opt), or composition files in the workspace. It writes only to the local workspace, and can perform read-only MCP lookups (terminology resolution, RM/AM type specs, guides, and…
orchestrator
Route work to the smallest useful ArkSpace agent, workflow, and skill set.
code-engineer
Implement, refactor, test, and debug software projects.