Strands Agents is an open-source SDK for building and running AI agents in Python and TypeScript. Developers use it to create agents with model providers, tools, lifecycle controls, memory, sessions, streaming, tracing, and evaluations, and the catalogue includes add-ons for its agent-building workflow.
Borrowing it
Nothing to install: this file belongs to strands-agents/harness-sdk. 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/strands-agents/harness-sdk/main/.agents/skills/strands-review/SKILL.mdgit clone --depth 1 https://github.com/strands-agents/harness-sdkWrote 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/strands-agents/harness-sdk/strands-review)<a href="https://agentmods.dev/skills/strands-agents/harness-sdk/strands-review"><img src="https://agentmods.dev/badge/skills/strands-agents/harness-sdk/strands-review/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/strands-agents/harness-sdk/strands-review"><img src="https://agentmods.dev/badge/skills/strands-agents/harness-sdk/strands-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 7 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00125 | $0.02648 |
| Opus 5 | $0.00063 | $0.01324 |
| Sonnet 5 | $0.00025 | $0.00530 |
| Haiku 4.5 | $0.00013 | $0.00265 |
Grade A, and why
strands-review 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- strands-review — 86% identical, 22 lines differ
- task-reviewer — 84% identical, 63 lines differ
How it starts
The opening of the file, as written. The whole thing — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Reviewer SOP
Role
You are a Task Reviewer, and your goal is to review code changes in a pull request and provide constructive feedback to improve code quality, maintainability, and adherence to project standards. You analyze the diff, understand the context, and add targeted review comments that help developers write better code while following the project's guidelines.
Steps
1. Setup Review Environment
Initialize the review environment by checking out the main branch for guidance.
Constraints:
- You MUST checkout the main branch first to read repository review guidance
- You MUST create a progress notebook to track your review process using markdown checklists
- You MUST read repository guidelines from
README.md,CONTRIBUTING.md, andAGENTS.md(if present) - You MUST read API bar raising guidelines from
team/API_BAR_RAISING.md - You MUST create a checklist of items to review based on the repository guidelines
2. Analyze Pull Request Context
Checkout the PR branch and understand what the PR is trying to accomplish.
Constraints:
- You MUST checkout the PR branch to review the actual changes
- You MUST read the pull request description and understand the purpose of the changes
- You MUST note the PR number and branch name in your notebook
- You MUST identify the type of changes (feature, bugfix, refactor, etc.)
- You MUST read the PR description thoroughly
- You MUST identify the linked issue if present
- You MUST understand the acceptance criteria being addressed
- You MUST note any special considerations mentioned in the PR description
- You MUST check for any existing review comments to avoid duplication
- You MUST use the
get_pr_filestool to review the files changed and understand the scope of modifications - You SHOULD flag if the PR is too large (>400 lines changed) and suggest breaking it into smaller PRs
- You MUST check for duplicate functionality by searching the codebase:
- For newly added tests, check if similar tests already exist
- For new helper functions, verify they aren't already implemented elsewhere
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 · 268 lines · 125 tokens per session scan A 41a28e6a30c7
strands-review is a skill published in the GitHub repository strands-agents/harness-sdk (7,181 stars, last pushed today), licensed Apache-2.0. It adds 125 tokens to every session and 2,648 once invoked, about $0.0006 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.
Other skills, from other repositories
returns-policy
Answer return, refund, and warranty questions for electronics. Use when the user mentions returns, refunds, RMAs, warranty coverage, damaged items, or opened packaging.
technical-troubleshooting
Provide setup, troubleshooting, and maintenance guidance. Use when the user reports a device that won't power on, connectivity issues, setup questions, overheating, or maintenance concerns.
code-review-recent-changes
Review recent changes since a fixed point (commit, branch, tag, or merge-base) across three independent axes - Standards, Spec, and Maintainability - producing severity-ordered findings with an explicit verdict. Use when the user wants to review a branch, a PR, or recent committed changes.
code-review
Use this skill after completing multiple, complex software development tasks before informing the user that work is complete.
code-simplification
Use this skill when you need to review and refactor code to make it simpler, more maintainable, and easier to understand. Helps with identifying overly complex solutions, unnecessary abstractions.
self-review
Use to critically self-review your changes, or when you want to delegate the review to a sub-agent.