Agent-Harness-Kit: Agent for Claude Code

.claude/agents/independent-reviewer.md

independent-reviewer is an agent for Claude Code from Eduardo-Salvador/Agent-Harness-Kit. It costs 20 tokens per session (209 once invoked), scanned A, original, MIT.

A fresh-context, read-only reviewer for checking completed software work against a written specification.

In plain words
What is it for?
Use it to reconstruct expected behavior, inspect evidence, identify specification violations, and recommend integration or linked remediation.
Why use it?
It gives acceptance decisions an independent check instead of relying on the implementer's explanation or conversation history.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is Eduardo-Salvador/Agent-Harness-Kit's own configuration. It tells Claude Code how to work on Agent-Harness-Kit itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Agent-Harness-Kit configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Eduardo-Salvador/Agent-Harness-Kit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Eduardo-Salvador/Agent-Harness-Kit/main/.claude/agents/independent-reviewer.md
Clone the repo
git clone --depth 1 https://github.com/Eduardo-Salvador/Agent-Harness-Kit

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 independent-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/eduardo-salvador/agent-harness-kit/independent-reviewer/github.svg)](https://agentmods.dev/agents/eduardo-salvador/agent-harness-kit/independent-reviewer)
Your own site
<a href="https://agentmods.dev/agents/eduardo-salvador/agent-harness-kit/independent-reviewer"><img src="https://agentmods.dev/badge/agents/eduardo-salvador/agent-harness-kit/independent-reviewer/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.

agentmods 80×15 button for independent-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/eduardo-salvador/agent-harness-kit/independent-reviewer"><img src="https://agentmods.dev/badge/agents/eduardo-salvador/agent-harness-kit/independent-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 209 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00020 $0.00209
Opus 5 $0.00010 $0.00105
Sonnet 5 $0.00004 $0.00042
Haiku 4.5 $0.00002 $0.00021

Measured 12d ago against content hash 3308a42270ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

independent-reviewer 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 12d 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/independent-reviewer.md · 8 lines

What it actually says

Start with no implementer conversation history. Follow harness/roles/reviewer-integrator.md and the completed task's bounded review profile. Treat the pinned executable task SPEC—not the original prompt, chat memory, handoff conclusions, or implementation rationale—as acceptance authority. Reconstruct the expected behavior and criterion matrix before inspecting the code, then verify the supplied evidence independently. Run automatically as non-blocking assurance; do not ask for human approval, reopen the completed node, stop unrelated ready work, edit implementation, or expand authority. Distinguish violations that require linked remediation from optional follow-ups. Round 2 receives only the SPEC, prior blocker IDs, correction delta, linked remediation, and related regression evidence. After a second changes-requested, stop and recommend task/acceptance rewrite, decomposition, or a genuine human product/risk decision—never round 3.

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. 12d ago First seen · 8 lines · 20 tokens per session scan A 3308a42270ce

Subscribe to this mod's changes

independent-reviewer is an agent published in the GitHub repository Eduardo-Salvador/Agent-Harness-Kit (6 stars, last pushed 3d ago), licensed MIT. It adds 20 tokens to every session and 209 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.