Borrowing it
Nothing to install: this file belongs to ysfAskri/archguardian. 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/ysfAskri/archguardian/master/.cursor/commands/baseline.mdgit clone --depth 1 https://github.com/ysfAskri/archguardianWrote 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/commands/ysfaskri/archguardian/baseline)<a href="https://agentmods.dev/commands/ysfaskri/archguardian/baseline"><img src="https://agentmods.dev/badge/commands/ysfaskri/archguardian/baseline/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/commands/ysfaskri/archguardian/baseline"><img src="https://agentmods.dev/badge/commands/ysfaskri/archguardian/baseline.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 | $0.00000 | $0.00120 |
| Opus 5.5 | $0.00000 | $0.00048 |
| Sonnet 5.5 | $0.00000 | $0.00024 |
| Haiku 4.5 | $0.00000 | $0.00012 |
Grade A, and why
baseline 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 1mo 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
Create or update an archguardian baseline for incremental adoption.
- Create/Update:
npx archguardian scan --update-baseline --format json - Custom path: add
--baseline <path>flag - Status: read
.archguard-baseline.json, summarize, run scan to compare - Clear: confirm with user first, then delete
.archguard-baseline.json
Baseline matching uses ruleId + file + message (not line numbers) — survives code edits.
Recommend committing .archguard-baseline.json to version control.
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.
- 1mo ago First seen · 10 lines · 0 tokens per session scan A 7211effb0750
baseline is a command published in the GitHub repository ysfAskri/archguardian (4 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 120 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
poly-check
Lint and check formatting with poly — apply no fixes; summarize findings and drift.
index
Universal zero-dependency linter and formatter. One pure-Rust binary (poly) that lints and formats 30 languages in-process — ruff, oxc, biome, mago and more compiled in — with a tree-sitter tier for the long tail. One config, git hooks, and an MCP server for agents.
debug
Systematic four-phase debugging (reproduce, isolate, root-cause, fix).
fix-issues
Pick up one approved task, implement the fix, and close it.
security-audit
Full security review — GitHub alerts, static code analysis, live app check — then a task per finding.
release
A typical CI release creates the release, associates commits, finalizes it, and records a deploy. The sentry release create examples above show the full sequence.