Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/matteotitta/genesys-skillsnpx agentmods add skills/matteotitta/genesys-skills/scope-guardian-reviewerWrote 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/matteotitta/genesys-skills/scope-guardian-reviewer)<a href="https://agentmods.dev/skills/matteotitta/genesys-skills/scope-guardian-reviewer"><img src="https://agentmods.dev/badge/skills/matteotitta/genesys-skills/scope-guardian-reviewer/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/matteotitta/genesys-skills/scope-guardian-reviewer"><img src="https://agentmods.dev/badge/skills/matteotitta/genesys-skills/scope-guardian-reviewer.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 | $0.00150 | $0.01363 |
| Opus 5 | $0.00075 | $0.00681 |
| Sonnet 5 | $0.00030 | $0.00273 |
| Haiku 4.5 | $0.00015 | $0.00136 |
Grade B, and why
scope-guardian-reviewer scanned grade B with 1 finding 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 12d 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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
4. **Don't moralize.** This isn't about whether the price is right; it's about whether the scope is bounded. How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scope-guardian reviewer
Review proposals, scope-of-work documents, and engagement plans for scope creep risks before they become unbillable rework. Adapted from ce-scope-guardian-reviewer agent in EveryInc/compound-engineering-plugin v3.5.0 (MIT).
The most expensive bug in a B2B SaaS consultancy is a proposal that promises everything. This reviewer catches it before send.
When to run
Invoke when the user says:
- "Run scope guard on [proposal]"
- "Is this proposal tight enough?"
- "Scope creep check"
- "Pre-send review on [SOW]"
- "Will this scope kill us?"
Do NOT invoke when:
- User wants voice review →
voice-reviewer - User wants product strategy review →
product-lens-reviewer - User wants legal contract review →
legal:review-contract
Composes with: product-lens-reviewer, voice-reviewer. Run as the last step before sending any client-facing scope document.
Inputs
Required:
- Proposal / SOW / engagement document text
Recommended:
win-loss-analysis— what scope patterns won/lost in the past- Prior client engagement records (in
projects/consulting/active/{client}/)
The 5 dimensions
| # | Dimension | Trigger |
|---|---|---|
| 1 | Open-ended deliverables | "ongoing support," "as needed," "TBD," "iterative refinement" without count → FAIL |
| 2 | Unbounded revisions | "unlimited revisions," "until satisfied," missing revision count → FAIL |
| 3 | Missing acceptance criteria | Each deliverable should have a measurable "done" definition. No criteria → WARN |
| 4 | Client-input dependencies | Deliverable depends on data/access/feedback the client hasn't committed to providing on a date → WARN/FAIL |
| 5 | Mission drift | Are deliverables in the original engagement's lane? A messaging engagement that includes "build a website" → FAIL |
Verdict logic
| Inputs | Verdict |
|---|---|
| All PASS | Send it |
| Any WARN, no FAIL | Tighten before send |
| Any FAIL | Don't send — rewrite |
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.
- 12d ago First seen · 131 lines · 150 tokens per session scan B 649601142d5c
scope-guardian-reviewer is a skill published in the GitHub repository matteotitta/genesys-skills (36 stars, last pushed 1mo ago), licensed MIT. It adds 150 tokens to every session and 1,363 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
gingiris-b2b-growth
🇺🇸 B2B SaaS Growth — PLG vs SLG Playbook — Diagnose whether your problem is distribution, pricing, or PMF. PLG/SLG selection by ACV and sales cycle, the 5-stage path from $0 to $10M ARR, NRR discipline, affiliate & channel motion, enterprise tiering. Built from HeyGen, Deel, Vercel, Supabase, Snowflake patterns.…
gr-b2b-growth
A guide to growing a business-to-business software product from early user research to large-scale sales. B2B software is sold to companies rather than individual consumers.
go-to-market-playbook
A reusable Go-to-Market strategy template for both B2B and B2C launches. Covers positioning, messaging, ICP definition, channel selection, and competitive analysis frameworks. By @WeiYipei.
data-privacy-compliance
Data privacy compliance for B2B SaaS — GDPR, CCPA/CPRA, ePrivacy Directive, cookie consent, Data Processing Agreements (DPAs), Standard Contractual Clauses (SCCs), Data Protection Impact Assessments (DPIAs), subject access requests (SARs), and privacy-by-design. Covers step-by-step compliance roadmap, privacy tech…
employment-compliance
Employment law and compliance for B2B SaaS founders — contractor vs employee classification, offer letters, IP assignment (PIIA), at-will employment, equity documentation, employee handbooks, harassment policies, termination procedures, and multi-state / international hiring compliance. Use when hiring first…
fundraising-strategy
Complete fundraising strategy for B2B SaaS founders. Use when preparing to raise seed/Series A, deciding VC vs bootstrapped path, building pitch deck, running a fundraise process, evaluating term sheets, or planning fundraising timeline. Covers SAFE, priced rounds, and bootstrapper alternatives.