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 agentmods add skills/evgenii-studitskikh/claude-code-saas-studio/scope-checknpx skills add evgenii-studitskikh/Claude-Code-SaaS-Studio --skill scope-checkgit clone --depth 1 https://github.com/evgenii-studitskikh/Claude-Code-SaaS-StudioWrote 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/evgenii-studitskikh/claude-code-saas-studio/scope-check)<a href="https://agentmods.dev/skills/evgenii-studitskikh/claude-code-saas-studio/scope-check"><img src="https://agentmods.dev/badge/skills/evgenii-studitskikh/claude-code-saas-studio/scope-check.svg" alt="Measured on agentmods" 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 | $0.00039 | $0.00492 |
| Opus 5 | $0.00019 | $0.00246 |
| Sonnet 5 | $0.00008 | $0.00098 |
| Haiku 4.5 | $0.00004 | $0.00049 |
Grade A, and why
scope-check 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 5d 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
Act as a scope guardian: read the PRD's goals, non-goals, and success metrics, then evaluate whether a proposed piece of work belongs in the current iteration. Non-autonomous: always surfaces findings and options before any decision is recorded.
Phases
- Load the PRD — read
docs/specs/prd.md. Extract the stated goals, in-scope user stories, and explicit non-goals. If the PRD does not exist, stop and direct the user to/write-prdfirst. - Understand the proposal — if no argument was given, ask the user to describe the feature or change under review in one or two sentences. Ask clarifying questions if the proposal is ambiguous.
- Evaluate alignment — compare the proposal against each PRD goal and non-goal. Score it: IN_SCOPE (clearly serves a stated goal), BORDERLINE (related but not explicitly scoped), or OUT_OF_SCOPE (matches a non-goal or adds unplanned complexity).
- Present options — for BORDERLINE or OUT_OF_SCOPE items, present three choices: (A) Cut it from this iteration and log it as a future idea, (B) Narrow it to the smallest version that fits scope, (C) Formally expand scope by updating the PRD. Explain the cost/risk of each option.
- Record the decision — once the user chooses, note the decision and, if the PRD is to be updated (option C), draft the minimal change to
docs/specs/prd.mdand await approval before writing. Once findings are resolved, return to the skill that invoked this check (e.g.,/build-feature) or continue the current phase.
Output
Text scope verdict + decision record. Updates docs/specs/prd.md only if the user chooses to expand scope and approves the draft change.
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.
- 5d ago First seen · 22 lines · 39 tokens per session scan A 6239c7c2812e
scope-check is a skill published in the GitHub repository evgenii-studitskikh/Claude-Code-SaaS-Studio (1 stars, last pushed 2mo ago), licensed MIT. It adds 39 tokens to every session and 492 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 2026-08-31.
Other skills, from other repositories
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
create-modal
Create declarative modals using the modal library API. Covers modal types (confirm, input, select, form), sections (Text, Buttons, Input, Textarea, Checkbox, Select, List, Combo, When, Custom), rendering with OverlayModal, and keyboard/mouse handling. Use when adding modals or dialogs to the application.
ap-juror
L4 terminal leaf - G7 SIGN-OFF. One independent sign-off panel seat that saw none of the intermediate work. Binary PASS/FAIL on opened evidence; default-FAIL. A FAIL naming a P0/P1 blocker is NOT arbitrable into PASS.
openlore-brainstorm
Transform a feature idea into an annotated story using a Domain Sketch or Constrained Option Tree. Use when asked to brainstorm, explore, or shape a feature before implementation.
gemigo-cli
Use when the user wants to publish an already-built static website or front-end app through GemiGo, such as a Vite/React/Vue static build, plain HTML/CSS/JS page, landing page, demo, docs site, or small browser app, and get a hosted public URL.
agenticx-query-data-source
Use when the user asks about verifiable quantitative facts (stock prices, financial indicators, macro data, company registry, academic metrics, legal statutes) that must come from a live data source rather than training memory.