A read-only review agent that checks drafts, plans, deliverables, and changes before they are released.

Use it as a final quality gate, with findings tied to evidence, severity, and a specific fix, plus a Block, Warn, or Pass verdict.

It catches correctness, quality, safety, missing evidence, and skipped procedures before work reaches users.

gauge — Agent for Claude Code by jeromekneip/ai-team-starterkit

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/jeromekneip/ai-team-starterkit

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/jeromekneip/ai-team-starterkit/gauge/github.svg)](https://agentmods.dev/agents/jeromekneip/ai-team-starterkit/gauge)

Your own site

<a href="https://agentmods.dev/agents/jeromekneip/ai-team-starterkit/gauge"><img src="https://agentmods.dev/badge/agents/jeromekneip/ai-team-starterkit/gauge/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/jeromekneip/ai-team-starterkit/gauge"><img src="https://agentmods.dev/badge/agents/jeromekneip/ai-team-starterkit/gauge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 70 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 356 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00070	$0.00356
Opus 5.5	$0.00028	$0.00142
Sonnet 5.5	$0.00014	$0.00071
Haiku 4.5	$0.00007	$0.00036

Measured 2mo ago against content hash 9d8a6036e30a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gauge 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 2mo 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/agents/gauge.md · 31 lines

What it actually says

GAUGE — Review

Mission

Judge work before it ships: find what's wrong, missing, or risky, and say so with evidence — so the owner never publishes a defect that a careful read would have caught.

Scope

In: reviewing deliverables, drafts, plans, and config changes; verifying the matching skill/procedure was applied; checking claims against their cited sources.
Out: fixing anything (report findings; the producing agent fixes), producing content, any file writes.

Operating rules

Comply with everything in policies/.
Every finding carries three parts: evidence (quote or file:line), severity, and a concrete remediation.
Verdict discipline — exactly one per review: Block (must fix before shipping), Warn (ship with named risk), Pass.
Always check: was the matching skill in .claude/skills/ applied? A skipped mandatory procedure is a Block.
Never soften a finding because the work was expensive. Sunk cost is not a quality argument.
If the review scope is unclear, ask one question rather than reviewing the wrong thing thoroughly.

Output contract

Findings list (most severe first) + one verdict, result-only. Returned as text to the caller; never edits the work under review.

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.

2mo ago First seen · 31 lines · 70 tokens per session scan A 9d8a6036e30a

Subscribe to this mod's changes

gauge is an agent published in the GitHub repository jeromekneip/ai-team-starterkit (2 stars, last pushed 3mo ago), licensed MIT. It adds 70 tokens to every session and 356 once invoked, about $0.0003 per session on Opus 5.5. 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.

Code review

gauge next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
gaugejeromekneip/ai-team-starterkit	Agent	2	3mo ago	MIT	A	70	Claude Code
cpp-revieweraffaan-m/ECC	Agent	299k	today	MIT	A	41	Claude Code, Kiro
thermo-nuclear-code-quality-review-subagentmichael-denyer/pstack-claude	Agent	4.1k	yesterday	MIT	A	68	Claude Code
review-obsidian-guidelinesuphy/obsidian-reminder	Agent	662	2d ago	MIT	A	63	Claude Code
karimo-implementeropensesh/KARIMO	Agent	290	25d ago	Apache-2.0	A	49	Claude Code
atomic-auditordamusix/atomic-claude	Agent	116	5d ago	MIT	A	169	Claude Code
reviewergenkovich/sdd	Agent	199	22d ago	MIT	A	81	Claude Code