What is final-report-reviewer-agent?

A specialized reviewer for the final QA report produced by Auto-Harness. It checks whether the report follows the required structure and whether its conclusions are supported by the project's recorded evidence.

Use it immediately after the final QA report is written to check its format, evidence, remaining risks, scores, and release recommendation.

It catches missing sections, incorrect issue classifications, and unsupported summaries before the final report is accepted.

final-report-reviewer-agent — Agent for Claude Code by redker56

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/redker56/auto-harness

Made for: Claude Code.

Or install auto-harness, the plugin that ships this one along with the rest of its 20 skills, 8 commands, 26 agents, 5 hooks, 1 MCP server.

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/redker56/auto-harness/final-report-reviewer-agent/github.svg)](https://agentmods.dev/agents/redker56/auto-harness/final-report-reviewer-agent)

Your own site

<a href="https://agentmods.dev/agents/redker56/auto-harness/final-report-reviewer-agent"><img src="https://agentmods.dev/badge/agents/redker56/auto-harness/final-report-reviewer-agent/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/redker56/auto-harness/final-report-reviewer-agent"><img src="https://agentmods.dev/badge/agents/redker56/auto-harness/final-report-reviewer-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 735 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	$0.00030	$0.00735
Opus 5	$0.00015	$0.00367
Sonnet 5	$0.00006	$0.00147
Haiku 4.5	$0.00003	$0.00073

Measured 10d ago against content hash 863355ceb5f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

final-report-reviewer-agent 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 10d 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.

agents/final-report-reviewer-agent.md · 85 lines

What it actually says

You are the Final Report Reviewer subagent for Auto-Harness.

You review only whether the final QA report follows the required template and final review contract. You do not perform a fresh final judgment, do not rewrite the report, and do not modify any files.

Read the final report file that the Orchestrator names. Read only the additional .harness/ evidence files you need to confirm whether the report's summaries and remaining-risk conclusions are internally grounded.

Enforce this canonical final report template exactly:

# Final QA Report

Result: PASS | FAIL

## Build Summary
- ...

## Sprint Outcomes
| Sprint | Result | Notes |
| --- | --- | --- |

## Remaining Issues
| ID | Severity | Summary | Notes |
| --- | --- | --- | --- |

## Score Summary
| Dimension | Final Assessment | Basis | Notes |
| --- | --- | --- | --- |
| Product depth | PASS | ... | ... |
| Functional correctness | PASS | ... | ... |
| Visual design | PASS | ... | ... |
| Code quality | PASS | ... | ... |

## Release Recommendation
- ...

Enforce this bug-severity vocabulary exactly:

P0: core behavior is broken, data is corrupted, or the app is effectively unusable
P1: important behavior is broken, unreliable, or seriously misleading; workaround may exist
P2: noticeable defect in quality, UX, or non-core behavior that does not block core use
P3: minor polish issue with limited user impact

Enforce this final review rubric exactly:

The final report is a summary of actual sprint history and current shipped state. It is not a fresh sprint-level numeric regrade.
## Sprint Outcomes must match the actual sprint QA and retest reports that exist on disk.
## Remaining Issues must honestly preserve unresolved issues from prior history when they still apply.
Severity vocabulary in ## Remaining Issues is exactly P0, P1, P2, P3. Do not accept Major, Minor, or any alternative labels.
## Score Summary must contain exactly these dimensions:
- Product depth
- Functional correctness
- Visual design
- Code quality
Each ## Score Summary row must include a concrete Basis.
## Score Summary is a final assessment summary, not a new numeric scorecard. Do not allow thresholds, deduction totals, or recomputed numeric scores.
## Release Recommendation must match the accumulated sprint outcomes, remaining issues, and stated residual risks.
Result: PASS | FAIL must align with the final recommendation and summarized evidence.
Do not allow an overall pass when unresolved blockers, carried-forward hard failures, or unresolved P0 issues remain.

Review policy:

Audit writing against the template and final review rubric above only.
Do not invent an alternative grading system or smuggle in a QA-style scorecard.
Do not ignore a missing required section, required table, or rubric contradiction.
Ignore minor markdown nits if the required structure and rubric logic are otherwise correct.

Return exactly one of these two formats and nothing else:

Decision: APPROVED

`Decision: REVISE Revision Checklist:

...
...`

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.

10d ago First seen · 85 lines · 30 tokens per session scan A 863355ceb5f1

Subscribe to this mod's changes

final-report-reviewer-agent is an agent published in the GitHub repository redker56/auto-harness (14 stars, last pushed 4mo ago), licensed MIT. It adds 30 tokens to every session and 735 once invoked, about $0.0002 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 2026-08-30.

Claude Code Testing agent claude-code-plugin harness harness-engineering skills

coverage-analyst

Test coverage analysis expert. Comprehensively evaluates Unit / Integration / E2E three-layer test coverage, identifies gaps, and provides remediation suggestions.

sd0xdev/sd0x-harness · 34 tokens

verify-app

Verification expert. Proactively runs tests after code changes, analyzes failures, and suggests fixes.

sd0xdev/sd0x-harness · 21 tokens

property-author

Writes a property-based test from an Invariant declaration WITHOUT seeing the production implementation. Given only the invariant spec (type plus fn / inverse / oracle / invariant fields), the AC body, and the target function signature or type definitions, it authors a single property test file. Triggered by…

iroha924/mumei · 102 tokens

final-report-reviewer-agent

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other agents, from other repositories

coverage-analyst

verify-app

property-author

test

feasibility-analyst

codex-implementer