compare

A command that compares two RepoVista run directories, such as an older run and a newer run. It can report differences as Markdown, JSON, or HTML.

In plain words
What is it for?
Use it in reviews or automation to detect new critical, high, or medium findings and enforce regression limits.
Why use it?
It makes it easier to see whether findings changed between runs and can stop with an error when new findings exceed chosen severity thresholds.

Command

Install

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.

agentmods
npx agentmods add commands/nordbyte/repovista/compare
Clone the repo
git clone --depth 1 https://github.com/nordbyte/RepoVista
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 304 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00304
Opus 5 $0.00000 $0.00152
Sonnet 5 $0.00000 $0.00061
Haiku 4.5 $0.00000 $0.00030

Measured 2d ago against content hash 24e2f7cb36f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

compare 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.

docs/commands/compare.md · 34 lines

What it actually says

compare

Compare two RepoVista run directories.

Usage

repovista compare <old-run-dir> <new-run-dir> [--format markdown|json|html] [--fail-on-regression]

Options

Option Purpose
--format <format> Output markdown, json, or html.
--json Alias for --format json for this command.
--fail-on-regression Exit 2 when new critical or high findings are detected.
--max-new-critical <n> Exit 2 when new critical findings exceed the threshold.
--max-new-high <n> Exit 2 when new high findings exceed the threshold.
--max-new-medium <n> Exit 2 when new medium findings exceed the threshold.

Examples

repovista compare .repovista/base .repovista/head
repovista compare .repovista/base .repovista/head --format json
repovista compare .repovista/base .repovista/head --fail-on-regression
repovista compare .repovista/base .repovista/head --max-new-critical 0 --max-new-high 0

Exit behavior

Compare returns exit code 2 for configured regression gates and 1 for usage or runtime failures.

Changes

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.

  1. 2d ago First seen · 34 lines · 0 tokens per session scan A 24e2f7cb36f4

Subscribe to this mod's changes

compare is a command published in the GitHub repository nordbyte/RepoVista (3 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 304 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 2026-08-31.