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/pre-push/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/pre-push)<a href="https://agentmods.dev/skills/strands-agents/harness-sdk/pre-push"><img src="https://agentmods.dev/badge/skills/strands-agents/harness-sdk/pre-push/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/pre-push"><img src="https://agentmods.dev/badge/skills/strands-agents/harness-sdk/pre-push.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00085 | $0.01335 |
| Opus 5.5 | $0.00034 | $0.00534 |
| Sonnet 5.5 | $0.00017 | $0.00267 |
| Haiku 4.5 | $0.00009 | $0.00134 |
Grade A, and why
pre-push 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 2mo 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pre-push Checks Skill
Get your branch push-ready: detect which areas your changes touch, auto-fix what's mechanically fixable, then run the same checks CI's merge gate runs for those areas — and triage whatever's left with the user.
This is a manually-invoked check, not a git hook — it runs only when you ask for it, so it never gets in the way of committing incrementally. Reach for it when you're about to push or open a PR. (When opening a PR, run this first, then use the pr-create / pr-writer skills to draft and open it.)
The repo's CI (.github/workflows/ci.yml) detects which of three areas changed and runs only those: python (strands-py/), typescript (strands-ts/), and docs (site/). This skill mirrors that routing locally.
Process
1. Run the bundled script
bash .agents/skills/pre-push/run-checks.sh 2>&1
Non-zero exit means something failed. On failure, the script prints a summary at the end with every failed step and the last 20 lines of its error output — everything you need to start fixing is in the tail of the output. Ignore noise earlier in the output.
The script runs from anywhere in the repo (it locates the root via git rev-parse --show-toplevel). From a subdirectory:
bash "$(git rev-parse --show-toplevel)/.agents/skills/pre-push/run-checks.sh"
It detects the changed areas — comparing against the closest main/master base it can find (local or any remote, so upstream/main on a fork works too — fork-aware), plus staged, unstaged, and untracked changes — using the same path filters CI uses, then for each detected area runs two phases:
- Phase 1 — auto-fix: formatting, lint
--fix, and lockfile sync. These are scoped to the files your change touches (so they never reformat unrelated files into your commit), write to working-tree files, and never fail the run. - Phase 2 — check: the gate (build, lint check, format check, type-check, tests, audit), run tree-wide for CI parity. Phase 2 runs on the now-fixed tree and decides pass/fail.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 74 lines · 85 tokens per session scan A 0da228c80df3
pre-push is a skill published in the GitHub repository strands-agents/harness-sdk (8,996 stars, last pushed today), licensed Apache-2.0. It adds 85 tokens to every session and 1,335 once invoked, about $0.0003 per session on Opus 5.5. 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
verify-changes
Verify code changes by running the project's typecheck, build, lint, and targeted tests, then fix and re-run until clean. Use after editing any source file.
agent-eval
Use when measuring whether an LLM or agent system actually got better and gating merges on it: golden sets, fixing an inflated LLM-as-judge, scoring RAG (faithfulness, contextual recall) or agent trajectories (tool correctness, completion), or picking an eval framework. NOT building the agent loop, tools or RAG…
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.
deepeval
Use when discussing or working with DeepEval (the python AI evaluation framework).
e2e-automation-project
Maintain a dedicated automation test project per repository - separate from the product's unit tests - with API, worker, and UI suites written scenario-first.