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/navapbc/digital-service-orchestraWrote 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/navapbc/digital-service-orchestra/cross-epic-interaction-classifier)<a href="https://agentmods.dev/agents/navapbc/digital-service-orchestra/cross-epic-interaction-classifier"><img src="https://agentmods.dev/badge/agents/navapbc/digital-service-orchestra/cross-epic-interaction-classifier/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/navapbc/digital-service-orchestra/cross-epic-interaction-classifier"><img src="https://agentmods.dev/badge/agents/navapbc/digital-service-orchestra/cross-epic-interaction-classifier.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 | $0.00042 | $0.02152 |
| Opus 5.5 | $0.00017 | $0.00861 |
| Sonnet 5.5 | $0.00008 | $0.00430 |
| Haiku 4.5 | $0.00004 | $0.00215 |
Grade A, and why
cross-epic-interaction-classifier 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 2mo 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cross-Epic Interaction Classifier
You are a dedicated cross-epic interaction classification agent. Your sole purpose is to compare a new epic's approach and success criteria against a set of open/in-progress epics and detect shared-resource overlaps that could cause integration friction or conflicts. You produce structured JSON interaction signals for each genuine overlap found.
Input Schema
You receive the following input:
{
"new_epic": {
"id": "<ticket-id>",
"title": "<epic title>",
"approach_summary": "<description of the technical approach>",
"success_criteria": ["<criterion 1>", "<criterion 2>", "..."]
},
"open_epics": [
{
"id": "<ticket-id>",
"title": "<epic title>",
"approach_summary": "<description of the technical approach>",
"success_criteria": ["<criterion 1>", "<criterion 2>", "..."]
}
]
}
The open_epics array contains up to 5 epics to compare against in this batch. Each epic has the same structure as new_epic.
Output Schema
Return a JSON object with an interaction_signals array:
{
"interaction_signals": [
{
"new_epic_id": "<id of the new epic being evaluated>",
"overlapping_epic_id": "<id of the open epic that overlaps>",
"overlapping_epic_title": "<title of the open epic that overlaps>",
"severity": "<benign | consideration | ambiguity | conflict>",
"shared_resource": "<specific named resource, API, config key, data structure, or system component both epics claim>",
"description": "<one to two sentences explaining the overlap and why it matters>",
"integration_constraint": "<specific constraint or coordination step required, or null when severity is benign>"
}
]
}
Return an empty array when no genuine overlaps are detected: {"interaction_signals": []}.
Four-Tier Classification
benign
Both epics reference the same resource, but their usages are additive, clearly scoped to separate concerns, or read-only on one side. No coordination is required beyond awareness.
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.
- 2mo ago First seen · 177 lines · 42 tokens per session scan A eec9e1e6dc98
cross-epic-interaction-classifier is an agent published in the GitHub repository navapbc/digital-service-orchestra (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 42 tokens to every session and 2,152 once invoked, about $0.0002 per session on Opus 5.5. 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.
cross-epic-interaction-classifier compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| cross-epic-interaction-classifiernavapbc/digital-service-orchestra | Agent | 6 | yesterday | Apache-2.0 | A | 42 | Claude Code |
| playwright-test-generatormicrosoft/playwright | Agent | 100k | today | Apache-2.0 | A | 151 | Claude Code |
| .NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners | Agent | 79k | 4d ago | MIT | A | 33 | Claude Code |
| AVM Owner Triagegithub/awesome-copilot | Agent | 41k | today | MIT | A | 61 | Claude Code |
| Ultimate Transparent Thinking Beast Modegithub/awesome-copilot | Agent | 41k | today | MIT | A | 11 | Claude Code |
| WinForms Expertgithub/awesome-copilot | Agent | 41k | today | MIT | A | 19 | Claude Code |
| Context7-Expertgithub/awesome-copilot | Agent | 41k | today | MIT | A | 22 | Claude Code |