Claude Agent SDK for Python is a Python interface for querying and interacting with Claude Code, an AI coding agent that can read, edit, and run commands in a project. Developers use it to build interactive Claude-powered applications with custom tools and hooks. The catalogue add-ons provide commands, agents, hooks, instructions, skills, plugins, and settings for Claude Code workflows.
Borrowing it
Nothing to install: this file belongs to anthropics/claude-agent-sdk-python. 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/anthropics/claude-agent-sdk-python/main/.claude/skills/verify/SKILL.mdgit clone --depth 1 https://github.com/anthropics/claude-agent-sdk-pythonWrote 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/anthropics/claude-agent-sdk-python/verify)<a href="https://agentmods.dev/skills/anthropics/claude-agent-sdk-python/verify"><img src="https://agentmods.dev/badge/skills/anthropics/claude-agent-sdk-python/verify/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/anthropics/claude-agent-sdk-python/verify"><img src="https://agentmods.dev/badge/skills/anthropics/claude-agent-sdk-python/verify.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 Supply Chain · line 14 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
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 | $0.00048 | $0.01045 |
| Opus 5.5 | $0.00019 | $0.00418 |
| Sonnet 5.5 | $0.00010 | $0.00209 |
| Haiku 4.5 | $0.00005 | $0.00104 |
Grade C, and why
verify scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
`scripts/download_cli.py` shells out to `curl https://claude.ai/install.sh | bash` Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`scripts/download_cli.py` shells out to `curl https://claude.ai/install.sh | bash` How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verifying the build scripts
The SDK itself is a library (drive it through import claude_agent_sdk), but
the scripts/ directory is a set of CLIs run by the release workflows.
Verify them by running them, not by importing them.
NEVER run the real installer
scripts/download_cli.py shells out to curl https://claude.ai/install.sh | bash
(and the PowerShell equivalent). Running it for real overwrites the claude
binary on the developer's machine. Do not run bash install.sh, and do not
invoke download_cli.py with latest/stable (or any case variant) against
the real network.
Instead, put stub curl / bash / powershell on a temp PATH and drive the
script under env -i with an isolated HOME (so find_installed_cli() cannot
discover the real binary and copy it into src/claude_agent_sdk/_bundled/).
The harness
SB=$(mktemp -d); mkdir -p $SB/stub $SB/home $SB/repo/src/claude_agent_sdk
cp scripts/{download_cli.py,build_wheel.py,update_cli_version.py,_cli_version_validation.py} $SB/repo/scripts/
printf '__cli_version__ = "2.1.208"\n' > $SB/repo/src/claude_agent_sdk/_cli_version.py
cat > $SB/stub/curl <<'EOF'
#!/bin/bash
out=""; prev=""; for a in "$@"; do [ "$prev" = "-o" ] && out="$a"; prev="$a"; done
echo "[stub curl] argv: $*" >> "$MARKER"
[ -n "$out" ] && printf '%b' "${CURL_BODY:-#!/bin/bash\necho hi\n}" > "$out"
exit ${CURL_EXIT:-0}
EOF
cat > $SB/stub/bash <<'EOF'
#!/bin/bash
{ echo "[stub bash] argc=$#"; for a in "$@"; do echo " <$a>"; done; } >> "$MARKER"
EOF
chmod +x $SB/stub/*
cd $SB/repo
env -i HOME=$SB/home PATH=$SB/stub:/usr/bin:/bin MARKER=$SB/m \
CLAUDE_CLI_VERSION=2.1.208 .venv/bin/python scripts/download_cli.py
run_command() captures the child's output, so the stubs must log to a
$MARKER file — printing to stderr is swallowed.
Flows worth driving
update_cli_version.py <version>— the whole validator surface is reachable here: a concrete version writes the file;latest/stable,v2.1.207,next,2.1, and a quote-breakout string each exit 1 with a distinct message and leave the file untouched.build_wheel.py --skip-sdist— reads the pin, then chains intodownload_cli.py. Rewrite_cli_version.pyin the sandbox to a moving tag / single quotes / garbage / delete it: each must fail before any subprocess is spawned.--cli-version <v>bypasses the pin (intentional escape hatch; the release workflow does not use it).download_cli.py— setCURL_BODYto an HTML error page or an empty string to prove the body check refuses it with no retry; empty thePATHto prove a missingcurlfails fast in one attempt;CURL_EXIT=22to prove a genuine transient failure still retries 3×.- The Windows path is unreachable on Linux. It is behind
platform.system() == "Windows". Drive it with a small runner thatpatch.object(m.platform, "system", return_value="Windows")and a stubpowershellthat reads the-Commandtext and honours$env:CLAUDE_CLI_INSTALL_SCRIPT. This is the one place where forcing the platform is legitimate.
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.
- 1mo ago First seen · 80 lines · 48 tokens per session scan C f499a4e88c29
verify is a skill published in the GitHub repository anthropics/claude-agent-sdk-python (8,301 stars, last pushed today), licensed MIT. It adds 48 tokens to every session and 1,045 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
validate-release-green
Run or inspect the local Release-Green observer for an exact base or combined PR candidate, separating hard failures, advisory drift and incomplete evidence. Use for maintainer preflight; full CI acceptance remains a separate requirement.
verify-and-ship
Choose proportionate validation, fix failures, update the changelog, commit, push, and create/update the pull request or merge request.
ship
Pre-release gate — run the full gate, responsive + render checks, then produce the release checklist (README badge/current/changelog). Use before tagging a release.
ship-workflow
Resumable shipping lifecycle: reconciles current Git and GitHub facts from any entry (dirty default or feature branch, local commits, published branch, open PR, existing manual or native stack, merged work), commits dirty work as lossless logical commits, publishes or reuses the PR, requires current CI and review…
AI Release Guardian
Analyze a git diff, map affected risks, select the tests that matter, detect coverage gaps on changed lines, run configurable quality gates, and produce a go/no-go release report with cited evidence. Recommends only; never merges or deploys.