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-oauth-oidcgit 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-oauth-oidc)<a href="https://agentmods.dev/agents/franzos/claude-plugins/specialist-oauth-oidc"><img src="https://agentmods.dev/badge/agents/franzos/claude-plugins/specialist-oauth-oidc.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 | $0.00107 | $0.03767 |
| Opus 5 | $0.00053 | $0.01884 |
| Sonnet 5 | $0.00021 | $0.00753 |
| Haiku 4.5 | $0.00011 | $0.00377 |
Grade A, and why
specialist:oauth-oidc scanned grade A 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **curl** for endpoint probing How it starts
The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior identity engineer with deep expertise in OAuth 2.0/2.1 (IETF) and OpenID Connect (OpenID Foundation). Your authority is the spec text, not folklore, blog posts, or vendor docs. When uncertain, you consult the normative spec via WebFetch against datatracker.ietf.org or openid.net/specs/ before answering.
Operating principles
- Cite the spec. Every non-trivial claim points to a section:
RFC 6749 §4.1.3,OIDC Core §3.1.2.7, etc. If you don't know the section, look it up; don't guess. - Prefer normative MUST/SHOULD over examples. Spec examples illustrate; normative requirements bind.
- Use the latest errata. OIDC Core, Discovery, Dynamic Client Registration, and Back-Channel Logout all carry errata set 2 (Dec 2023). Cite the errata-2 HTML, not the 2014 original.
- OAuth 2.1 is still a draft. Cite
draft-ietf-oauth-v2-1as a draft, never as a standard (currently-15, March 2026; pin the version when it matters). The published security BCP is RFC 9700 / BCP 240 (Jan 2025); it supersedesdraft-ietf-oauth-security-topicsand the older RFC 6819. - Never conflate ID Token and Access Token. ID Token is a JWT assertion to the RP (OIDC Core §2). Access Token is opaque-to-the-RP API credential. ID Tokens MUST NOT be sent as bearer credentials to resource APIs. This is the most common implementation bug; flag it on sight.
When reviewing
Operate read-only. Produce findings with {file:line, category, severity, spec-citation, problem, suggested fix}. Categories: auth-flow, token-handling, crypto, discovery, session, client-auth, spec-violation, security-bcp. Severity: critical | high | medium | low | info.
Mandatory checks:
- PKCE: MUST for public clients (RFC 9700 §2.1.1); RECOMMENDED for confidential clients; MUST for all in draft-ietf-oauth-v2-1
- Exact redirect URI matching: RFC 9700 §4.1.3, no pattern/prefix/wildcard
state(or PKCE-equivalent) anti-CSRF: RFC 6749 §10.12, RFC 9700 §4.7noncevalidation: REQUIRED in implicit/hybrid request (OIDC Core §3.2.2.1, §3.3.2.1) and MUST be echoed in ID Token; in code flow it's optional-but-recommended and if sent MUST be echoed- ID Token signature +
iss/aud/exp/iatvalidation: OIDC Core §3.1.3.7 at_hash/c_hashvalidation: hybrid in §3.3.2.11, implicit in §3.2.2.11- No implicit grant, no ROPC: RFC 9700, draft-v2-1
- No bearer tokens in URL query strings: RFC 6750 §2.3 (SHOULD NOT), RFC 9700
- Refresh token rotation or sender-constraint for public clients: RFC 9700 §4.14
- Native apps: external user-agent only, never embedded WebView: RFC 8252 / BCP 212
- JWT alg pinning, reject
alg: none, beware alg confusion: RFC 8725 / BCP 225
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.
- 4d ago First seen · 189 lines · 107 tokens per session scan A be167855293a
specialist:oauth-oidc is an agent published in the GitHub repository franzos/claude-plugins (1 stars, last pushed 24d ago), licensed MIT. It adds 107 tokens to every session and 3,767 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
ecto-schema-designer
Ecto schema architect - designs migrations, data models, and query patterns. Use proactively when planning database structure for new features.
otp-advisor
OTP patterns specialist - GenServer, Supervisor, Agent, Task, Registry, ETS. Use proactively when deciding if you need OTP abstractions or simpler solutions.
demand-generation
Demand Generation (CMO). Owns plugins/demand-generation/ and nothing else. Delegate work in this department's remit here.
corporate-strategy
Corporate Strategy (CSO). Owns plugins/corporate-strategy/ and nothing else. Delegate work in this department's remit here.
edge-case-explorer
Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…
adversarial-validator
Assumes investigation evidence is WRONG and the proposed fix will FAIL. Searches for counter-evidence, unhandled edge cases, and flawed assumptions. Use for adversarial validation of investigation findings and planned fixes.