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 BlackBeltTechnology/pi-agent-dashboard --skill switch-extension-sourcegit clone --depth 1 https://github.com/BlackBeltTechnology/pi-agent-dashboardWrote 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/blackbelttechnology/pi-agent-dashboard/switch-extension-source)<a href="https://agentmods.dev/skills/blackbelttechnology/pi-agent-dashboard/switch-extension-source"><img src="https://agentmods.dev/badge/skills/blackbelttechnology/pi-agent-dashboard/switch-extension-source.svg" alt="Measured on agentmods" 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 5 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 41 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 42 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 43 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 44 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 73 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 | $0.00063 | $0.00947 |
| Opus 5 | $0.00032 | $0.00474 |
| Sonnet 5 | $0.00013 | $0.00189 |
| Haiku 4.5 | $0.00006 | $0.00095 |
Grade A, and why
switch-extension-source 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 8d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Toggle a monorepo extension between npm (published) and local (working tree) source.
Why this exists
GUI equivalent: Settings → Packages exposes a per-row Reset to published version action (change: reset-override-to-npm) that resets a local/git-installed row back to its canonical
npm:<name>— install-first / remove-second, confirm-gated. It is the one-click UI analog ofswitch <pkg> npmhere; keep the two semantically aligned (both drop the localpackages[]registration only, never the working-tree files).
On a dev machine you want extensions to load your live working tree so edits take effect. Distribution users consume the published npm package. Both can be wired at once across two config layers, and whichever pi resolves last wins — non-deterministic ("I edited it but nothing changed"). This skill enforces exactly one source per package.
GLOBAL ~/.pi/agent/settings.json "packages": [...]
npm -> "npm:<npmName>"
local -> "<repoRoot>/packages/<dir>" (dir path; pi resolves package.json "pi")
PROJECT <repo>/.pi/settings.json "packages":[{ source, extensions:["+packages/<dir>/<entry>"] }]
local overlay -> only with --overlay; loads ONLY inside this repo; needs pi.extensions
local (default) = global dir path → loads in every session everywhere.
local --overlay = project overlay → loads only when running pi inside this repo.
Commands
npx tsx ./scripts/switch-source.ts status # where each installed pkg loads from
npx tsx ./scripts/switch-source.ts local <pkg> # -> local working tree (global path)
npx tsx ./scripts/switch-source.ts local <pkg> --overlay# -> local, this-repo-only (extensions only)
npx tsx ./scripts/switch-source.ts npm <pkg> # -> published npm build
<pkg> = monorepo dir name (kb-extension) OR npm name (@blackbelt-technology/pi-dashboard-kb-extension).
Each switch removes all other representations of that package, timestamped-backs-up every file it
edits (*.bak-switch-*), and re-validates JSON before writing.
What ships with it
3 files 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.
- 8d ago First seen · 76 lines · 63 tokens per session scan A 79310d03ae31
switch-extension-source is a skill published in the GitHub repository BlackBeltTechnology/pi-agent-dashboard (276 stars, last pushed yesterday), licensed MIT. It adds 63 tokens to every session and 947 once invoked, about $0.0003 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
akigitcommit
Analyze the working tree and commit changes in clean logical groups. Triages a long half-finished tree first (finished vs mid-edit vs abandoned vs accidental) before grouping. Auto-detects CHANGELOG to switch between domain-grouped mode (3–5 commits by object/feature) and type-grouped mode (feat/fix/refactor). Stages…
akiship
Full release ritual end-to-end — front-loaded checks, then an unattended pass. ACTIVATION IS LITERAL: this skill runs only on a user turn containing the exact token /akiship that asks for the run to be performed. Nothing else activates it — not the bare word "akiship", not a release-flavored paraphrase, and never a…
public-plugin-packaging
Use when packaging an Agentlas agent repo for public GitHub release, Codex plugin submission, Claude adapter distribution, or one-line terminal installation.
commit
Atomic git commit with conventional message. Use when the user says "commit", "save my changes", "commit this", or wants to create a git commit. Stages specific files, writes a conventional commit message with body explaining non-obvious decisions. Never uses git add -A.
apply-patch
Apply multi-file or tricky edits atomically with git apply instead of many fragile editfile calls. Use when changing several files at once or when editfile fails to match.
git-checkpoint
Use git as a safety net - create a checkpoint commit before risky or large changes and roll back cleanly if a change makes things worse. Use before multi-file refactors.