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/authentication-client/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/authentication-client)<a href="https://agentmods.dev/skills/greenpau/go-authcrunch/authentication-client"><img src="https://agentmods.dev/badge/skills/greenpau/go-authcrunch/authentication-client/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/authentication-client"><img src="https://agentmods.dev/badge/skills/greenpau/go-authcrunch/authentication-client.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 | $0.00049 | $0.02532 |
| Opus 5.5 | $0.00020 | $0.01013 |
| Sonnet 5.5 | $0.00010 | $0.00506 |
| Haiku 4.5 | $0.00005 | $0.00253 |
Grade A, and why
authentication-client 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 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.
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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Authentication Client
Ownership
pkg/authclient is the importable consumer of pkg/apiauth JSON login types.
It owns Config, Client, Options, PromptFunc, Credentials, and
FileTokenStore. It sends only POST <base_url>/login; authentication does not
require enable admin api. Keep server handlers in pkg/authn and management
operations in cmd/authdbctl.
Read references/integration.md when embedding the
client, choosing credential paths, or changing the CLI adapter. Public contracts
also live beside the exported Go declarations and in pkg/authclient/doc.go.
The reusable package does not discover config, select application directories,
read terminal input, log credentials, or dispatch CLI commands. Do not add
urfave/cli, term, or application-name defaults to it. Applications own prompt
presentation, config loading, user-agent identity, and credential persistence.
Protocol Invariants
NewClientvalidates a copy of configuration.Authenticate(ctx)starts a fresh exchange, returns credentials, and has no token-file side effects.- Keep each response newly decoded. Missing sandbox fields must not inherit previous response values. Continue only with a sandbox ID, sandbox secret, and next challenge; success requires a nonempty usable access token.
- Keep the ten-request bound, response-size limit, context propagation, and refusal to follow redirects, including with an injected HTTP client.
- Configured password/TOTP values avoid input prompts.
PromptMFAreturnstotporwebauthn; the CLI translates numbered choices. Without a prompt, a configured TOTP secret can answer a combined MFA challenge directly. APIKeyselects a separate, single-request login withRealm; reject mixed username/password/TOTP configuration. Send the key only in the JSON body, never in the URL. Do not fall back to challenges or prompt after key rejection. The portal derives the identity using its existing proxy API key verifier. Keys are independent credentials, including for accounts enrolled in MFA. They do not satisfy password/TOTP/WebAuthn checkpoints; configured challenge requirements or an explicit saved flow preference can therefore deny key login. Key login issues an access token only, sets no cookies, and cannot create a refresh family.refresh_transport: bodyis rejected for this mode.- TOTP uses raw secret bytes and SHA-1, matching
identity.MfaTokenand existing authdbctl config. Do not silently interpret the secret as base32. Defaults are six digits and thirty seconds; accepted digits match the portal's four-to-eight range and the period must be positive. - U2F/WebAuthn assertion handling remains unsupported. Return
ErrUnsupportedChallengewithout echoing server challenge payloads. Missing input usesErrInputRequired; HTTP failures expose a status viaHTTPError. - Each login returns only its new credentials. Never merge an old refresh token into a fresh result. Token syntax checks are not JWT verification.
What ships with it
2 files 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.
- 12d ago Changed b1bf6fedaa86
- 28d ago Changed · -1 lines a83bab3e1ae0
- 1mo ago Changed · +2 lines · -22 tokens per session 8d2fefef32c6
- 1mo ago Changed · +42 lines · +9 tokens per session 817deedae63f
- 1mo ago First seen · 150 lines · 62 tokens per session scan A 02aafbdbfb7c
authentication-client is a skill published in the GitHub repository greenpau/go-authcrunch (60 stars, last pushed 10d ago), licensed Apache-2.0. It adds 49 tokens to every session and 2,532 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.
authentication-client compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| authentication-clientgreenpau/go-authcrunch | Skill | 60 | 10d ago | Apache-2.0 | A | 49 | 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 |