baseline

baseline is a skill for Claude Code from ysfAskri/archguardian. It costs 18 tokens per session (370 once invoked), scanned A, original, MIT.

A tool for recording existing code-quality findings in a baseline file so a project can adopt scanning gradually. Later scans can focus on findings that are new instead of reporting every old issue.

In plain words
What is it for?
Use it to create or update an archguardian baseline, check its status, compare scans with it, or clear it after confirming that all findings should be shown again.
Why use it?
It prevents pre-existing problems from overwhelming a team when they first introduce the scanner.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

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 skills/ysfaskri/archguardian/baseline
Any agent
npx skills add ysfAskri/archguardian --skill baseline
Clone the repo
git clone --depth 1 https://github.com/ysfAskri/archguardian

Made for: Claude Code.

Wrote 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.

agentmods badge for baseline

README.md
[![agentmods](https://agentmods.dev/badge/skills/ysfaskri/archguardian/baseline.svg)](https://agentmods.dev/skills/ysfaskri/archguardian/baseline)
Your own site
<a href="https://agentmods.dev/skills/ysfaskri/archguardian/baseline"><img src="https://agentmods.dev/badge/skills/ysfaskri/archguardian/baseline.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 370 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 5.1 $0.00018 $0.00370
Opus 5 $0.00009 $0.00185
Sonnet 5 $0.00004 $0.00074
Haiku 4.5 $0.00002 $0.00037

Measured 5d ago against content hash 6131a5108f08, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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 5d 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.

.claude/skills/baseline/SKILL.md · 54 lines

What it actually says

archguardian baseline

Manage the archguardian baseline file for incremental adoption.

Instructions

Determine the user's intent from $ARGUMENTS (create, update, status, clear):

Create / Update baseline

  1. Run:
    npx archguardian scan --update-baseline --format json
    
  2. Report how many findings were saved to .archguard-baseline.json.
  3. Remind the user that future scans will only show NEW findings not in the baseline.
  4. Suggest committing .archguard-baseline.json to version control.

Custom baseline path

If the user specifies a path:

npx archguardian scan --update-baseline --baseline <path> --format json

Check baseline status

  1. Check if .archguard-baseline.json exists:
    ls -la .archguard-baseline.json
    
  2. If it exists, read and summarize: how many findings, when generated, by which command.
  3. Run a scan to show how many new vs baseline findings there are.

Clear baseline

If the user wants to remove the baseline:

  1. Confirm with the user first.
  2. Delete .archguard-baseline.json.
  3. Warn that the next scan will report all findings again.

Tips

  • Baseline matching uses ruleId + file + message (not line numbers), so it survives code edits that shift line numbers.
  • Recommend creating a baseline when first adopting archguardian on a large existing codebase.
  • The baseline should be updated periodically as tech debt is paid down.
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. 5d ago First seen · 54 lines · 18 tokens per session scan A 6131a5108f08

Subscribe to this mod's changes

baseline is a skill published in the GitHub repository ysfAskri/archguardian (4 stars, last pushed 6mo ago), licensed MIT. It adds 18 tokens to every session and 370 once invoked, about $0.0001 per session on Opus 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.