donaldfilimon/abi / .agents/skills/auth-localcheck
auth-localcheck
VerifiedBuild the abi CLI and check the credential/auth surface without storing, deleting, or transmitting anything — `auth status` (provider table) and `auth signin` usage banner. Use to smoke-test the auth command wiring after touching credential code. Never writes or deletes credentials and never hits the network.
auth-localcheck — drive abi's auth surface (non-destructive)
Driver: .agents/skills/auth-localcheck/auth.sh (paths relative to repo root).
Builds the CLI and exercises only the safe auth surfaces. Evidence is the
RESULT: line. No creds written/deleted, no network.
Run (agent path)
.agents/skills/auth-localcheck/auth.sh
auth status→ assertsAuthentication Status:,OpenAI:,Anthropic:,Twilio:.auth signin(no service) → asserts theusage: abi auth signinbanner (validates the subcommand is wired; stores nothing).
Prints RESULT: PASS (exit 0) or a FAIL count.
Current Rust driver: builds target/debug/abi, checks the provider status
table, and proves bare signin reaches the usage-only path without writing.
Gotchas
- ⚠️
auth logoutis destructive — it deletes any stored credentials. The driver deliberately does NOT run it, and does NOT run a realauth signin <svc>(which would store creds). Do those manually when you actually intend to change credential state. - Overlap note:
connector-localcheckalso touchesauth status; this skill is the auth-lifecycle-focused check (status + signin wiring) and stays credential-safe. - Real remote calls (
complete --live, live connector transport) requireauth signin <svc>first; that path is intentionally out of scope here. - For a source-level audit of credential validation + the live/local boundary,
use the
connector-validatorsubagent.
Troubleshooting
| Symptom | Fix |
|---|---|
build FAIL | Check the repository toolchain via ./tools/cargo.sh --version, then ./tools/check.sh. |
Authentication Status: missing | Handler grammar drift — check crates/abi-cli/src/auth.rs and ../wdbx/crates/abi-foundation/src/credentials/. |
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |