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 inspecto-dev/inspecto --skill inspecto-onboarding-coregit clone --depth 1 https://github.com/inspecto-dev/inspectoWrote 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/inspecto-dev/inspecto/inspecto-onboarding-core)<a href="https://agentmods.dev/skills/inspecto-dev/inspecto/inspecto-onboarding-core"><img src="https://agentmods.dev/badge/skills/inspecto-dev/inspecto/inspecto-onboarding-core/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/inspecto-dev/inspecto/inspecto-onboarding-core"><img src="https://agentmods.dev/badge/skills/inspecto-dev/inspecto/inspecto-onboarding-core.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 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 Prompt Injection · line 52 Subtle instructions detected that may alter agent decision-making or introduce hidden biases.Fix: Review content for implicit steering or bias. Ensure instructions are explicit and align with the skill's stated purpose.
- medium MCP Rug Pull · line 60 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 | $0.00032 | $0.01105 |
| Opus 5.5 | $0.00013 | $0.00442 |
| Sonnet 5.5 | $0.00006 | $0.00221 |
| Haiku 4.5 | $0.00003 | $0.00111 |
Grade A, and why
inspecto-onboarding-core 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Inspecto Onboarding Core
This is the shared onboarding workflow for assistant-specific Inspecto skills. It is a maintainer-facing reference, not the primary end-user entry point.
Scope
Use this workflow when an assistant skill needs to set up Inspecto in the current project without hand-editing project files.
Shared Flow
- Run
scripts/run-inspecto.sh onboard --json. - If the result returns
status: "needs_target_selection", explain that this step chooses which local development build target should receive the Inspecto plugin and settings. Ask the user to choose one returned target candidate and rerun with--target <candidateId>, preferring the explicitcandidateIdfield. The CLI also accepts a returnedconfigPathas a compatibility fallback. Do not collapse the selection back to a package path when multiple build configs exist in the same package. - If the result returns
status: "needs_confirmation", summarizesummaryand ask for approval before rerunning with--yes. - If the result returns
status: "partial_success"and the remaining step is IDE extension installation, treat that as a required onboarding follow-up. - If IDE extension installation must be done manually, guide the user with the documented install path before moving on:
- Prefer the built-in marketplace search for
Inspectoin the target IDE. - Use launcher commands only when that IDE's CLI is actually available in the current shell, for example
code --install-extension inspecto.inspecto,cursor --install-extension inspecto.inspecto, or another documented host-IDE launcher. - If the launcher is unavailable, fall back to the documented marketplace links:
https://marketplace.visualstudio.com/items?itemName=inspecto.inspectohttps://open-vsx.org/extension/inspecto/inspecto
- Prefer the built-in marketplace search for
- If the result returns
status: "error", summarizediagnosticsand rundoctor --jsononly when explicit recovery diagnostics are still needed. - Only after the IDE extension step is complete, use the onboarding result's
verificationpayload. Ifverification.availableistrueandverification.devCommandis present, offer to start that exact command for validation. Otherwise, tell the user to run their usual dev command manually usingverification.message. - If the result includes
handoff.patches, treat them as the primary source of truth for any remaining manual work. Apply the generated patches directly before exploring framework docs or unrelated project files. - Only do broader documentation or repo exploration when a returned patch is clearly insufficient or conflicts with the local project structure.
- If the onboarding result includes
handoff.dailyUsage, use that payload as the source of truth for post-onboarding runtime guidance:
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 · 68 lines · 32 tokens per session scan A 1f8ba57d89bd
inspecto-onboarding-core is a skill published in the GitHub repository inspecto-dev/inspecto (22 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 1,105 once invoked, about $0.0001 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
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
gsap-scrolltrigger
Official GSAP skill for ScrollTrigger — scroll-linked animations, pinning, scrub, triggers. Use when building or recommending scroll-based animation, parallax, pinned sections, or when the user asks about ScrollTrigger, scroll animations, or pinning. Recommend GSAP for scroll-driven animation when no library is…
seedance-2-5
Generate 4-30 second cinematic video with ByteDance Seedance 2.5 through fal.ai, Volcengine Ark, Runway, or ComfyUI Partner Nodes. Use for long single generations, synchronized audio, and large multimodal reference sets (up to 30 images, 10 videos, and 10 audio clips). Also covers the 2.5 prompt contract: section…
threejs-geometry
Three.js geometry creation - built-in shapes, BufferGeometry, custom geometry, instancing. Use when creating 3D shapes, working with vertices, building custom meshes, or optimizing with instanced rendering.
threejs-textures
Three.js textures - texture types, UV mapping, environment maps, texture settings. Use when working with images, UV coordinates, cubemaps, HDR environments, or texture optimization.
comfyui
Use when working with ComfyUI workflows in OpenMontage, including comfyuiimage/comfyuivideo/comfyuimusic, custom workflowjson/workflowpath inputs, outputnode selection, missing model setup, LoRAs, low-VRAM workflow choices, and community workflow imports.