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 spences10/my-pi --skill pi-package-sandbox-testgit clone --depth 1 https://github.com/spences10/my-piWrote 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/spences10/my-pi/pi-package-sandbox-test)<a href="https://agentmods.dev/skills/spences10/my-pi/pi-package-sandbox-test"><img src="https://agentmods.dev/badge/skills/spences10/my-pi/pi-package-sandbox-test/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/spences10/my-pi/pi-package-sandbox-test"><img src="https://agentmods.dev/badge/skills/spences10/my-pi/pi-package-sandbox-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 6 findings, up to medium
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 →
- medium MCP Rug Pull · line 23 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 26 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 30 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 31 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 36 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 37 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00040 | $0.00539 |
| Opus 5 | $0.00020 | $0.00269 |
| Sonnet 5 | $0.00008 | $0.00108 |
| Haiku 4.5 | $0.00004 | $0.00054 |
Grade A, and why
pi-package-sandbox-test 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 12d 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
Pi Package Sandbox Test
Verify published packages work for normal Pi users, independent of
my-pi.
Procedure
- From the repository root, enumerate
packages/*/package.json. - Select only packages with a
pimanifest; helper/internal packages withoutpiare not user-installable Pi packages. - For each selected package, compare local
package.jsonversion withnpm view <pkg> version. - In a disposable Daytona sandbox via
pnpx ralph-town run, use vanilla Pi only:pnpx @earendil-works/pi-coding-agent - For each published npm version, verify both commands succeed:
pnpx @earendil-works/pi-coding-agent install npm:<package>@<npm-version> pnpx @earendil-works/pi-coding-agent -e npm:<package>@<npm-version> --help - In the same clean sandbox config, install all selected packages
together, then run:
pnpx @earendil-works/pi-coding-agent list pnpx @earendil-works/pi-coding-agent --help
Report Format
Report a compact table with:
- package name
- local version
- npm version
- install result
- ephemeral load result
- notes
Call out local/npm version drift separately. Version drift is not a
failure when it is explained by release timing, changesets, or
minimumReleaseAge; the user-facing check should use the published
npm version that normal Pi users can install.
Failure Patterns
Treat these as failures unless explained by the sandbox environment:
- npm package cannot be resolved
pi install npm:<package>@<version>exits non-zeropi -e npm:<package>@<version> --helpexits non-zero- startup output includes
Cannot find module,ERR_MODULE_NOT_FOUND,SyntaxError,TypeError, orReferenceError - packages pass alone but fail when installed together
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.
- 12d ago First seen · 67 lines · 40 tokens per session scan A 88bac5971a28
pi-package-sandbox-test is a skill published in the GitHub repository spences10/my-pi (125 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 539 once invoked, about $0.0002 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
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
ship
Ship phase. Runs isolated integration test in a fresh worktree, creates a PR with full spec + audit report in the body, watches CI, and auto-fixes failures.
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.
gh-credit-harvest
Harvest one community PR into a release branch with authorship and credit preserved, verified green, and a warm thank-you.
release
Prepare a named version: preflight, version consistency, build/package, smoke test, checksums/notes, and release readiness. Publishing/tagging/deploy need separate authorization. Explicit-only.
tmux-manual-qa
Run a single manual tmux-based QA scenario for the todo continuation feature against the real CLI (./pi-test.sh) in an interactive TUI. Captures scrollback, asserts deterministic pass/fail count markers, and cleans up test fixtures. Use only for the manual-qa milestone features.