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.
npx skills add ntorga/agent-starter-kit --skill reviewer-handoffgit clone --depth 1 https://github.com/ntorga/agent-starter-kitWrote 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/skills/ntorga/agent-starter-kit/reviewer-handoff)<a href="https://agentmods.dev/skills/ntorga/agent-starter-kit/reviewer-handoff"><img src="https://agentmods.dev/badge/skills/ntorga/agent-starter-kit/reviewer-handoff/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/skills/ntorga/agent-starter-kit/reviewer-handoff"><img src="https://agentmods.dev/badge/skills/ntorga/agent-starter-kit/reviewer-handoff.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 | $0.00016 | $0.00362 |
| Opus 5 | $0.00008 | $0.00181 |
| Sonnet 5 | $0.00003 | $0.00072 |
| Haiku 4.5 | $0.00002 | $0.00036 |
Grade A, and why
reviewer-handoff 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 2d 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.
What it actually says
Purpose
This skill defines the output format for review handoffs — the structured summary a Reviewer delivers after inspecting work. The progress file (.memory/reviews/review-<type>-<timestamp>.md) contains the full findings trail. The handoff adds the verdict and planned commits on failure.
Procedure
- Assemble the handoff using the template below. The progress file path is required — it contains all findings.
## Review Summary
**Verdict:** <pass | partial-pass | fail>
**Type:** <code | architecture | documentation | configuration | other>
**Progress file:** <path to review progress file>
## SHIELD Self-Review Scorecard
[Complete the scorecard from `skills/reviewer-self-review/SKILL.md`]
-
Determine the verdict.
pass— zero blockers and all review phases completed.partial-pass— zero blockers but a review phase was skipped (e.g., external tool unavailable).fail— one or more blockers.
-
Append planned commits on failure. When the verdict is
failand the type iscode, add a "Planned Commits" section after the summary. Write conventional-commit messages (follows:rules/git.md) for each requested fix. This gives the next step ready-made commit messages once the fixes land.
Guardrails
- Never omit the Progress file reference — it contains the full analysis trail and is required on every review.
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.
- 2d ago First seen · 38 lines · 16 tokens per session scan A 5b5784e9e8dc
reviewer-handoff is a skill published in the GitHub repository ntorga/agent-starter-kit (142 stars, last pushed 2d ago), licensed MIT. It adds 16 tokens to every session and 362 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 2026-09-13.
Other skills, from other repositories
pragma-code-review
A code-review guide written in Chinese. It reviews code across correctness, architectural boundaries, risk, and verification.
safe-refactor
Refactor checklist with guardrails.
agent-framework-py-release
Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
build-and-test
How to build and test .NET projects in the Agent Framework repository. Use this when verifying or testing changes.
python-feature-lifecycle
Guidance for package and feature lifecycle in the Agent Framework Python codebase, including stage meanings, feature-stage decorators, feature enums, and how to move APIs from one stage to the next.