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 J-StaR-Films-Studios/VibeCode-Protocol-Suite --skill role-deliverygit clone --depth 1 https://github.com/J-StaR-Films-Studios/VibeCode-Protocol-SuiteWrote 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/j-star-films-studios/vibecode-protocol-suite/role-delivery)<a href="https://agentmods.dev/skills/j-star-films-studios/vibecode-protocol-suite/role-delivery"><img src="https://agentmods.dev/badge/skills/j-star-films-studios/vibecode-protocol-suite/role-delivery/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/j-star-films-studios/vibecode-protocol-suite/role-delivery"><img src="https://agentmods.dev/badge/skills/j-star-films-studios/vibecode-protocol-suite/role-delivery.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 | $0.00042 | $0.01058 |
| Opus 5.5 | $0.00017 | $0.00423 |
| Sonnet 5.5 | $0.00008 | $0.00212 |
| Haiku 4.5 | $0.00004 | $0.00106 |
Grade A, and why
role-delivery 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.
How it starts
The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role delivery
The user's requested outcome is the scope boundary. Do not fix unrelated issues.
Choose the role
Obey a role named by the user. Otherwise classify the task as:
- Frontend
- Backend
- Backend and frontend
- Review only
State the classification in one sentence before substantial work.
Frontend agent
Own pages, components, forms, navigation, interaction states, responsive behavior, and integration with existing backend contracts.
Before coding, identify the required queries, mutations, arguments, return values, authorization rules, and error states. Follow the existing design system. Do not invent backend behavior or weaken backend authorization.
Run focused component tests, the affected app typecheck, and the affected app build.
If a required backend contract does not exist, stop and provide this copyable handoff:
You are the backend agent.
Implement only the backend contract required for this frontend task.
Required behavior:
<behavior>
Required queries or mutations:
<contracts>
Authorization and tenant rules:
<rules>
Expected success and error states:
<states>
Do not redesign the frontend. Return the exact callable contract, files changed,
tests run, and any migration or deployment requirement.
Continue the frontend only after the real backend contract exists.
Backend agent
Own schema and data integrity, queries, mutations, actions, authentication, authorization, tenant isolation, storage, quota, cleanup, audit behavior, migrations, and compatibility.
Read repository backend guidance before editing. Keep the backend authoritative and fail closed at security boundaries. Add focused integration tests and run the backend typecheck.
Do not create UI unless the user assigned backend-and-frontend work. Before finishing, state whether users can access the operation through an existing UI.
If frontend work remains, provide this copyable handoff:
You are the frontend agent.
The backend contract is complete. Build the smallest UI that exposes it.
Actor and application:
<actor and app>
Queries and mutations:
<exact contracts>
Success and failure states:
<states>
Permission and visibility rules:
<rules>
Relevant backend files:
<paths>
Do not change backend behavior unless you find a confirmed contract defect.
Report that defect instead of expanding the task.
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 · 149 lines · 42 tokens per session scan A e8aa6fcb998d
role-delivery is a skill published in the GitHub repository J-StaR-Films-Studios/VibeCode-Protocol-Suite (24 stars, last pushed yesterday), licensed ISC. It adds 42 tokens to every session and 1,058 once invoked, about $0.0002 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 2026-09-13.
Other skills, from other repositories
effect-ledger
Record an effect, sign an effect, reconcile an effect or check "did this PR merge" through the signed AIWG effect ledger, using one aiwg effect command with scriptable exit codes.
github
Interact with GitHub using the gh CLI. Use gh issue, gh pr, gh run, and gh api for issues, PRs, CI runs, and advanced queries.
gsd-quick-batch
Batch several /gsd-quick-shaped tasks together — planned, dispatched, and merged as one run.
gsd-pause-work
Create context handoff when pausing work mid-phase.
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
gait-session-tracking
GAIT session lifecycle management - branch creation, turn recording, audit logging for every NetClaw operation. Use when starting a new NetClaw session, recording a health check or config change, pinning a pre-change baseline, or viewing the audit trail for a troubleshooting session.