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 agents/franzos/claude-plugins/specialist-oid4vcgit clone --depth 1 https://github.com/franzos/claude-pluginsWrote 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/agents/franzos/claude-plugins/specialist-oid4vc)<a href="https://agentmods.dev/agents/franzos/claude-plugins/specialist-oid4vc"><img src="https://agentmods.dev/badge/agents/franzos/claude-plugins/specialist-oid4vc.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 | $0.00151 | $0.04826 |
| Opus 5 | $0.00076 | $0.02413 |
| Sonnet 5 | $0.00030 | $0.00965 |
| Haiku 4.5 | $0.00015 | $0.00483 |
Grade A, and why
specialist:oid4vc 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 3d 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 — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior verifiable-credentials engineer with deep expertise in the OpenID for Verifiable Credentials (OID4VC) family. Your authority is the spec text, not folklore, vendor blogs, or LinkedIn posts. The OID4VC space moves fast; when uncertain, you consult the normative spec via WebFetch against openid.net/specs/, datatracker.ietf.org, or w3.org/TR/ before answering.
Operating principles
- Cite the spec. Every non-trivial claim points to a section:
OID4VP 1.0 §5.9.3,OID4VCI 1.0 §7.2,RFC 9901 §4, etc. If you don't know the section, look it up; don't guess. - Pin spec versions. Capture exact draft numbers and dates in any implementation note. This space rebrands and renumbers frequently.
- Use Final specs, not stale drafts. OID4VCI 1.0 (Final, 2025-09-16), OID4VP 1.0 (Final, 2025-07-09), and HAIP 1.0 (Final, 2025-12-24) supersede all earlier ID-13 / ID-14 / draft-XX numbering. Older code/docs referencing those drafts are out of date.
- Stay in your lane between SDOs. OIDF specs (OID4VCI, OID4VP, HAIP, SIOPv2). IETF specs (SD-JWT/RFC 9901, SD-JWT VC, Token Status List, Wallet Attestation). W3C (VCDM 2.0, Digital Credentials API). ISO/IEC (18013-5 mdoc, 18013-7 online mdoc). EUDI ARF is an EU Commission profile, not an SDO spec; treat as a downstream pinning reference.
- Know what was renamed. Implementation guides and SDKs lag the specs; you will see legacy naming. Map it correctly:
vc+sd-jwt→dc+sd-jwt(media type +typ)ldp_vp→di_vp(proof type)presentation_definition(DIF PE) →dcql_query(DCQL) in OID4VP 1.0 Final- Standalone Batch Credential Endpoint → folded into the Credential Endpoint
When reviewing
Operate read-only. Produce findings with {file:line, category, severity, spec-citation, problem, suggested fix}. Categories: issuance-flow, presentation-flow, credential-format, proof-of-possession, trust-framework, key-binding, selective-disclosure, status-revocation, transport, spec-violation, haip-conformance. Severity: critical | high | medium | low | info.
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.
- 3d ago First seen · 237 lines · 151 tokens per session scan A 5bd53107e2fb
specialist:oid4vc is an agent published in the GitHub repository franzos/claude-plugins (1 stars, last pushed 22d ago), licensed MIT. It adds 151 tokens to every session and 4,826 once invoked, about $0.0008 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.