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 ambystechcom/AmbyKit --skill amby-reviewgit clone --depth 1 https://github.com/ambystechcom/AmbyKitWrote 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/ambystechcom/ambykit/amby-review)<a href="https://agentmods.dev/skills/ambystechcom/ambykit/amby-review"><img src="https://agentmods.dev/badge/skills/ambystechcom/ambykit/amby-review/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/ambystechcom/ambykit/amby-review"><img src="https://agentmods.dev/badge/skills/ambystechcom/ambykit/amby-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00021 | $0.00356 |
| Opus 5.5 | $0.00008 | $0.00142 |
| Sonnet 5.5 | $0.00004 | $0.00071 |
| Haiku 4.5 | $0.00002 | $0.00036 |
Grade A, and why
amby-review 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 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.
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
Review the user's request that followed this skill invocation (an artifact path, e.g. specs/NNN-slug/spec.md) as a different role.
If the path does not exist, stop and name the phase that produces it.
- Pick the reviewer:
--as <id>→@.amby/roles/<id>.md; otherwise QA for a spec or tasks, Architect for a plan, PM for a UI design. If the file is missing, stop and list.amby/roles/. Say which role you are acting as in your first line. - Read only the artifact (and its spec, if reviewing a plan or tasks). Apply the role's focus
checklist. Produce findings, one per line:
ID · severity (high/med/low) · finding · fix— every finding names a stable ID (US-#,FR-###,SC-###,T###). Modify nothing. - Only with
--apply: patch the artifact in place for each finding, preserving every existing ID (never renumber), then append under a## Reviewsheading at the end:- <date> · <role> · <n> findings applied— orapprovedwhen there were none. - This is advisory: no phase waits on a review. End with the findings count and the next phase to run.
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 · 20 lines · 21 tokens per session scan A 7351e060ab80
amby-review is a skill published in the GitHub repository ambystechcom/AmbyKit (2 stars, last pushed 2d ago), licensed MIT. It adds 21 tokens to every session and 356 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 2026-08-31.
Other skills, from other repositories
importing-a-codebase
Use when asked to create the initial spec graph for an existing codebase that has source code but no specs. Normally reached via setting-up-a-project.
starting-a-new-project
Use when the workspace is empty, has no code, and the user brings a raw project idea. Normally reached via setting-up-a-project; not for an existing project.
managing-mcp-servers
Use when the user asks to add, change, remove, enable or disable an MCP server, or when an MCP tool is missing, needs sign-in, fails, or was blocked. ThinkRail runs pi in-process, so there is no pi command to call.
todos
Use when the user asks for a shared plan, a task needs at least three substantive execution steps, or a loose TODO is pending. Without an explicit plan request, not for one-shot answers or checks, or one- to two-step work that is not already in the list.
asking-user-questions
Use when composing an askuserquestion round inside a workflow, or when a workflow skill names it at a question step. Shared norms for the tool — not a workflow, nothing to execute.
writing-workflow-skills
Use when adding a new workflow skill to pi-thinkrail-workflow, changing an existing workflow skill's role, trigger, handoff, or structure, or checking a workflow skill against the workflow system's rules. Not for authoring general-purpose skills outside this package.