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 commands/nordbyte/repovista/auditgit clone --depth 1 https://github.com/nordbyte/RepoVistaWhat 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 | $0.00000 | $0.00518 |
| Opus 5 | $0.00000 | $0.00259 |
| Sonnet 5 | $0.00000 | $0.00104 |
| Haiku 4.5 | $0.00000 | $0.00052 |
Grade A, and why
audit 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.
What it actually says
audit
Run a full repository audit. repovista with no command is an alias for repovista audit.
Usage
repovista [options]
repovista audit [options]
Common options
- Source and scope:
--github-repo,--github-ref,--since,--pr,--base,--workspace,--all-workspaces,--workspace-matrix - Provider:
--provider,--model,--profile,--reasoning,--fast,--sandbox - Mode:
--audit-profile,--review-mode,--bug-findings - Quality:
--run-checks,--check,--strict-reports,--repair-reports,--repair-attempts,--deep-review - Output:
--out,--resume,--export,--json,--keep-logs - CI gates:
--ci,--fail-on-critical,--fail-on-drift,--fail-on-weak-evidence,--min-quality-score,--max-critical,--max-high,--max-medium
See CLI options for every flag and accepted value.
Examples
repovista audit
repovista audit --model gpt-5.5
repovista audit --provider claude --model sonnet --reasoning high
repovista audit --github-repo nordbyte/RepoVista
repovista audit --github-repo https://github.com/nordbyte/RepoVista --github-ref v0.4.0
repovista audit --bug-findings
repovista audit --github-repo nordbyte/RepoVista --bug-findings
repovista audit --since origin/main
repovista audit --ci --json --fail-on-critical
repovista audit --phase risk-and-bug --phase summary
Output
The default output root is .repovista. Each run gets a timestamped directory with index.md, phase reports, JSON summaries, exports, findings, and metadata.
With --bug-findings, RepoVista writes the Risk/Bug report and the supporting JSON/state/export artifacts needed to inspect findings and publish selected ones as GitHub issues or PRs. It does not generate architecture, code-quality, roadmap, summary, or deep-review reports for that run.
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.
- 2d ago First seen · 43 lines · 0 tokens per session scan A 759a1ef88cdb
audit 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 518 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.
Other commands, from other repositories
brooks-audit
Run a Brooks-Lint architecture audit.
release
The pre-tag controller: version sync, changelog, clean tree, gate, and suite — every failure listed, the tag printed, never run.
security
The security pass: secrets (blocking), SAST, dependency vulns — plus the index's entry points to review from.
init
Install the formatters this repository needs, with every command visible before it runs.
VibeGuard: Cross Review
Dual-model adversarial review — Claude generates review reports, Codex does adversarial verification, and iterates until convergence.
al
Run AgentLint diagnostic across all projects. Use when: user says /al, 'check all projects', 'agent lint', or '体检'.