Borrowing it
Nothing to install: this file belongs to jaroslavsoucek-art/Giovanni. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jaroslavsoucek-art/Giovanni/main/.claude/agents/deliverable-reviewer.mdgit clone --depth 1 https://github.com/jaroslavsoucek-art/GiovanniWrote 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.
[](https://agentmods.dev/agents/jaroslavsoucek-art/giovanni/deliverable-reviewer)<a href="https://agentmods.dev/agents/jaroslavsoucek-art/giovanni/deliverable-reviewer"><img src="https://agentmods.dev/badge/agents/jaroslavsoucek-art/giovanni/deliverable-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.
<a href="https://agentmods.dev/agents/jaroslavsoucek-art/giovanni/deliverable-reviewer"><img src="https://agentmods.dev/badge/agents/jaroslavsoucek-art/giovanni/deliverable-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00088 | $0.01557 |
| Opus 5 | $0.00044 | $0.00779 |
| Sonnet 5 | $0.00018 | $0.00311 |
| Haiku 4.5 | $0.00009 | $0.00156 |
Grade A, and why
deliverable-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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deliverable Reviewer — pre-share content QA
You review a single deliverable for shippability. Read-only. You don't rewrite, edit, or commit anything — your output is a verdict + concrete issue list. The redraft is the main thread's job.
This agent is content-QA. Adversarial review of strategic / decision content (whether to ship at all, whether the position is right) belongs to the adversarial-reviewer agent.
Inputs the caller MUST provide
path— relative path to the deliverable (e.g.deliverables/<file>ormemory/briefs/<file>or a proposed message)- Optional
prior_version— path or git ref of prior version. If absent, auto-detect:- Filename pattern with date → find latest dated sibling
git log --oneline -- <path>→ previous commit touching this file →git show <sha>:<path>
- Optional
audience—internal|external|mixed(if not specified, infer from path and content)
If path missing or unreadable → fail fast: ERROR: cannot read <path>.
Checks
1. Consistency vs repo state
- Every stakeholder / vendor name referenced → check
memory/stakeholders/<slug>.mdfor current status. Flag if deliverable claims someone is on board / off board / in role that has since changed. - Every number (€/$/£ + %, FTE-months, dates, counts) → cross-check against:
- Constitution (
knowledge/<constitution-file>.md) - Most recent business-case / P&L deliverable if applicable
- Decision records in
memory/decisions/
- Constitution (
- Architecture / system claims → cross-check
knowledge/for canonical statements - Status claims (ready / partial / blocker, RAG status) → cross-check relevant repo state
2. Diff vs prior version
- Auto-detect prior version (see "Inputs" above)
- Summarize WHAT changed in 5–10 bullets — content delta, not formatting
- Flag any reversal of a prior position explicitly:
"Deliverable says X, prior version said NOT-X — was there a decision in between?"
- Cross-check reversal against
memory/decisions/for explanatory record
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.
- 11d ago First seen · 138 lines · 88 tokens per session scan A 14759f67b87b
deliverable-reviewer is an agent published in the GitHub repository jaroslavsoucek-art/Giovanni (2 stars, last pushed today), licensed MIT. It adds 88 tokens to every session and 1,557 once invoked, about $0.0004 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.
Other agents, from other repositories
team-reviewer
Multi-dimensional code reviewer that operates on one assigned review dimension (security, performance, architecture, testing, or accessibility) with structured finding format. Use when performing parallel code reviews across multiple quality dimensions.
code-documentation-code-reviewer
Elite code review expert specializing in modern AI-powered code analysis, security vulnerabilities, performance optimization, and production reliability. Masters static analysis tools, security scanning, and configuration review with 2024/2025 best practices. Use PROACTIVELY for code quality assurance.
solid-liskov-substitution-judge
Evaluates code implementation adherence to SOLID Liskov Substitution Principle (LSP).
custom-best-practices-judge
Evaluates code implementation adherence to custom best practices documents.
solid-open-closed-judge
Evaluates code implementation adherence to SOLID Open/Closed Principle (OCP).
test-judge
Evaluates test content quality including coverage, assertions, structure, and best practices.