Borrowing it
Nothing to install: this file belongs to greenpau/go-authcrunch. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/greenpau/go-authcrunch/main/.codex/skills/claims-enrichment/SKILL.mdgit clone --depth 1 https://github.com/greenpau/go-authcrunchWrote 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/greenpau/go-authcrunch/claims-enrichment)<a href="https://agentmods.dev/skills/greenpau/go-authcrunch/claims-enrichment"><img src="https://agentmods.dev/badge/skills/greenpau/go-authcrunch/claims-enrichment/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/greenpau/go-authcrunch/claims-enrichment"><img src="https://agentmods.dev/badge/skills/greenpau/go-authcrunch/claims-enrichment.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 | $0.00041 | $0.02706 |
| Opus 5.5 | $0.00016 | $0.01082 |
| Sonnet 5.5 | $0.00008 | $0.00541 |
| Haiku 4.5 | $0.00004 | $0.00271 |
Grade A, and why
claims-enrichment 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 29d 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 — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claims Enrichment
Ownership and integration
pkg/authz/enrichment owns the Backend.Lookup(context.Context, Request)
interface, Config, Identity, Result, and New(config, backend) constructor.
plugins/claims-enrichment/static adds configured JSON claims in the root Go
module. Its New and Lookup APIs require no external service, credential, host
framework, registration side effect, or cleanup. It supplies the same configured
values to each identity accepted by the consumer's binding.
Construct a backend and enricher, then call
Gatekeeper.SetClaimsEnricher(*enrichment.Enricher) or
TokenValidator.SetClaimsEnricher(*enrichment.Enricher) before serving requests.
A nil attachment fails without changing the active attachment. Closed validators
reject attachment. Nil validators and nil/unconstructed gatekeepers return an
error without panicking, so failed host provisioning cannot crash attachment.
The host owns backend cleanup; drain requests before replacing
an attachment or closing the backend. Construct a new detached runtime for reload.
There is no global registry or JSON backend loader in root Config or authdb.
The validator invokes enrichment after authentication and before all eight ACL
request guardians, once per decision even when a path has multiple interpretations.
JWT and credential cache hits and public AuthorizeUser evaluations take this
path. Direct OAuth policy sessions use AuthorizeUser; its input must still
satisfy this feature's explicit issuer, realm, subject, tenant and audience binding.
An OAuth provider that does not produce those claims cannot use the hook without
a trusted adapter supplying them. Explicit gatekeeper bypass routes remain bypasses.
Enriched claims are only used by the ACL decision. The returned authenticated user, cache, identity headers, request identity, and original JWT retain their original claims. Neither initial portal issuance, refresh issuance nor downstream OIDC issuance runs this hook. Renewed tokens are enriched when subsequently used on an attached protected route. Do not describe this as token revocation or an issuance-time enrichment feature.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 29d ago First seen · 230 lines · 41 tokens per session scan A 86aea64ea38b
claims-enrichment is a skill published in the GitHub repository greenpau/go-authcrunch (60 stars, last pushed 10d ago), licensed Apache-2.0. It adds 41 tokens to every session and 2,706 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 2026-10-08.
claims-enrichment compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| claims-enrichmentgreenpau/go-authcrunch | Skill | 60 | 10d ago | Apache-2.0 | A | 41 | Codex |
| mem0-oss-to-platformmem0ai/mem0 | Skill | 68k | 2d ago | Apache-2.0 | A | 217 | Claude Code, Codex |
| azure-mgmt-botservice-dotnetmicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 78 | Claude Code |
| fastapi-router-pymicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 46 | Claude Code |
| dev-runtimelangwatch/langwatch | Skill | 5.0k | yesterday | Apache-2.0 | A | 172 | Claude Code |
| api-designericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 105 | Claude Code, Codex |
| migrate-segw-to-raparc-mcp/arc-1 | Skill | 252 | yesterday | MIT | A | 106 | Claude Code |