baseline-verifier

baseline-verifier is an agent for Claude Code from tomcounsell/ai. It costs 32 tokens per session (2,192 once invoked), scanned D, original, GPL-3.0.

A subagent that compares failing tests with the main code branch to classify failures as new regressions or pre-existing problems. A regression is a failure introduced by a recent change.

In plain words
What is it for?
Use it after tests fail when you need to check whether the failure also occurs on the main branch and record the resulting classification.
Why use it?
It helps distinguish defects caused by current work from failures that were already present, preventing incorrect conclusions about a change.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it after tests fail when you need to check whether the…

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/tomcounsell/ai/baseline-verifier
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.

Clone the repo
git clone --depth 1 https://github.com/tomcounsell/ai

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-verifier

README.md
[![agentmods](https://agentmods.dev/badge/agents/tomcounsell/ai/baseline-verifier.svg)](https://agentmods.dev/agents/tomcounsell/ai/baseline-verifier)
Your own site
<a href="https://agentmods.dev/agents/tomcounsell/ai/baseline-verifier"><img src="https://agentmods.dev/badge/agents/tomcounsell/ai/baseline-verifier.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,192 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 2 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown 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 $0.00032 $0.02192
Opus 5 $0.00016 $0.01096
Sonnet 5 $0.00006 $0.00438
Haiku 4.5 $0.00003 $0.00219

Measured 6d ago against content hash 2fd442ff3300, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade D, and why

baseline-verifier scanned grade D with 2 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 6d 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: ['*']

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf "$BASELINE_DIR" 2>/dev/null || true
.claude/agents/baseline-verifier.md · 241 lines

The source is not reproduced here

Licensed GPL-3.0

The repository is licensed GPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

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. 6d ago First seen · 241 lines · 32 tokens per session scan D 2fd442ff3300

Subscribe to this mod's changes

baseline-verifier is an agent published in the GitHub repository tomcounsell/ai (24 stars, last pushed yesterday), licensed GPL-3.0. It adds 32 tokens to every session and 2,192 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it D with 2 findings (unrestricted tool access, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

senior-developer

Use this agent when the user needs programming tasks executed, including feature implementation, refactoring, bug fixing, code reviews, or any code-related work. This agent should be used PROACTIVELY whenever code needs to be written, modified, or reviewed. It strictly follows Test-Driven Development…

jonase47/ccpr · 587 tokens

sequant-testgen

Test stub generator for sequant /testgen phase. Parses verification criteria from /spec comments and generates Jest/Vitest test stubs with Given/When/Then structure. Use when spawned by the /testgen skill.

sequant-io/sequant · 49 tokens

sequant-qa-checker

Quality check agent for sequant /qa phase. Runs type safety, scope/size, security, and documentation checks on diffs. Use when spawned by the /qa skill to perform parallel or sequential quality checks.

sequant-io/sequant · 50 tokens

task-validator

Validates task files against task template and task-creator rules. Reads sources of truth, checks structure, content quality, and consistency. Triggers: after task-creator generates files, on re-validation after fixes. Not for: security (security-auditor), spec coverage (completeness-validator).

stepanenkoviktor0110-boop/ai-dev-methodology · 63 tokens

tech-spec-validator

Validates tech-spec template compliance and implementation task quality: sections present, frontmatter correct, standards compliance, verification plan, task skill correctness, task brevity, decisions placement. Security, adequacy, testing strategy, and code mirage detection handled by dedicated validators. Use before…

stepanenkoviktor0110-boop/ai-dev-methodology · 71 tokens

userspec-quality-validator

Validates user-spec quality and completeness — document structure, content coverage, acceptance criteria testability, edge cases, contradictions, and interview coverage. Scope: document quality only. Solution adequacy (feasibility, overengineering, alternatives, stack compatibility) is handled by…

stepanenkoviktor0110-boop/ai-dev-methodology · 92 tokens