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-agentgit 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-agent)<a href="https://agentmods.dev/skills/inspecto-dev/inspecto/inspecto-agent"><img src="https://agentmods.dev/badge/skills/inspecto-dev/inspecto/inspecto-agent/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-agent"><img src="https://agentmods.dev/badge/skills/inspecto-dev/inspecto/inspecto-agent.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 Excessive Agency · line 32 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 33 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00033 | $0.00617 |
| Opus 5.5 | $0.00013 | $0.00247 |
| Sonnet 5.5 | $0.00007 | $0.00123 |
| Haiku 4.5 | $0.00003 | $0.00062 |
Grade A, and why
inspecto-agent 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Inspecto Agent
Use this skill when the user wants the AI to work from Inspecto annotations instead of manually restating page context in chat.
When to use
- The user asks the AI to run Inspecto in continuous mode.
- The user says to handle the next Inspecto annotation.
- The user asks the AI to continue or finish an Inspecto session.
- The user wants the AI to review, edit, or resolve work that was created in
Annotate mode.
Workflow
- Confirm the
inspectoMCP server is available. - If the user provided a
sessionId, callinspecto_get_sessionfirst and continue from that session. - Otherwise call
inspecto_claim_nextto wait for and acknowledge the next pending session. - If
inspecto_claim_nexttimes out or returns no session, call it again unless the user asked you to stop. - Read the claimed session and summarize the intended work briefly before making edits.
- After you begin real work, send a short progress update with
inspecto_reply. - If the work requires clarification, ask the user in chat and also leave a concise
inspecto_replynote so the session history stays complete. - When the task is complete, call
inspecto_resolvewith a short final summary. - If the session is invalid, duplicated, or should be closed without code changes, call
inspecto_dismisswith a short note instead. - For continuous mode, return to step 3 after resolving or dismissing.
Guardrails
- Do not ask the user to copy the page context or rewrite the annotation as a long prompt.
- Do not ask the user to restate page context if
inspecto_claim_nextorinspecto_get_sessionalready provides it. - Do not use list, latest, watch, or manual acknowledge tools as a task pickup path;
inspecto_claim_nextis the continuous entrypoint. - Do not rely on a later reply to imply pickup when claiming a task; claim it first.
- Do not resolve a session until the requested work is actually complete.
- Do not leave duplicate or invalid sessions hanging open when
inspecto_dismissis the clearer outcome. - Prefer concise progress replies that help the browser-side session history stay readable.
- If there are multiple plausible sessions and the user did not request continuous mode, present the top candidates briefly and ask which one to handle.
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 · 49 lines · 33 tokens per session scan A 3b73ee59f911
inspecto-agent is a skill published in the GitHub repository inspecto-dev/inspecto (22 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 617 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.