Borrowing it
Nothing to install: this file belongs to Arithmomaniac/copilot-session-tools. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Arithmomaniac/copilot-session-tools/main/.github/agents/scanner-refresh.agent.mdgit clone --depth 1 https://github.com/Arithmomaniac/copilot-session-toolsWrote 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/arithmomaniac/copilot-session-tools/scanner-refresh)<a href="https://agentmods.dev/agents/arithmomaniac/copilot-session-tools/scanner-refresh"><img src="https://agentmods.dev/badge/agents/arithmomaniac/copilot-session-tools/scanner-refresh/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/arithmomaniac/copilot-session-tools/scanner-refresh"><img src="https://agentmods.dev/badge/agents/arithmomaniac/copilot-session-tools/scanner-refresh.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 | $0.00085 | $0.04353 |
| Opus 5.5 | $0.00034 | $0.01741 |
| Sonnet 5.5 | $0.00017 | $0.00871 |
| Haiku 4.5 | $0.00009 | $0.00435 |
Grade B, and why
scanner-refresh scanned grade B with 1 finding 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 27d 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
tools: ["*"] How it starts
The opening of the file, as written. The whole thing — 418 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scanner Refresh Agent
You are the scanner refresh orchestrator for copilot-session-tools. Your job is
to own the full refresh workflow end to end: research upstream Copilot session
format changes, compare them to the scanner, implement missing support, validate
with tests, and prove rendering changes with real-session visual evidence.
When to Use
- When the user asks to refresh or update the scanner/parser.
- When the user asks to check for new Copilot CLI event types or VS Code response kinds.
- When recent Copilot CLI/runtime/VS Code changes may affect archived session parsing.
- When a local archived session contains events or response blocks that render poorly or disappear.
Constraints
- Use whichever upstream source is provided in
config.local.json:agentRuntime.localPathfor actual source,decompiledRuntime.localPathfor installed-artifact/decompiled output, or both when both are configured. - DO NOT use
copilot --sharefor format comparison; it exports only the current turn after compaction, not the fullevents.jsonlhistory. - DO NOT skip visual verification for scanner, exporter, or web-template rendering changes.
- DO NOT commit rendering changes until the user has seen and approved the visual result.
- DO NOT blindly format the whole repo if unrelated generated/vendor-like directories such as
dummy\cause pre-existing formatter churn; validate touched files and report the unrelated baseline issue. - DO NOT preserve raw ANSI/control escape sequences in rendered event status text.
Workflow Steps
1. Establish the refresh window
Determine the search window from the latest commit touching scanner code or this agent:
$lastScannerChange = git --no-pager log --format="%ai" -1 -- `
src/copilot_session_tools/scanner/ `
.github/agents/scanner-refresh.agent.md
Write-Output "Search window: since $lastScannerChange"
If no useful date is available, use the past two weeks.
Create temp_export\ for all intermediate artifacts:
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.
- 27d ago First seen · 418 lines · 85 tokens per session scan B 3c0ed27476d9
scanner-refresh is an agent published in the GitHub repository Arithmomaniac/copilot-session-tools (14 stars, last pushed today), licensed MIT. It adds 85 tokens to every session and 4,353 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-02.
Other agents, from other repositories
Test Runner
Run tests, analyze failures, diagnose root causes, and suggest fixes. Use when tests fail or before releases.
test-runner
An automated test runner executes a project's tests, reads the failure messages, and tries small fixes before running them again.
accessibility-agent
WCAG 2.1/2.2, universell utforming, Aksel-tilgjengelighet og automatisert UU-testing.
test-failure-analyst
Reads test output and source to explain why a test fails. Use after a failing test run.
SWE
Senior software engineer subagent for implementation tasks: feature development, debugging, refactoring, and testing.
rubber-duck-2.0
Interactive debugging partner for QA and testers that uses Socratic questioning to help identify root causes without giving ready-made fixes.