Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Issue and revoke short-lived Gateway bearer tokens. Run `smithers token --help` for usage details.
.claude/skills/smithersai-smithers-token/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-14 | ✗→✓ | ▲ Improved | -63% | 0% |
| case-01 | ✗→✓ | ▲ Improved | -4% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -1% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -42% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -31% | 0% |
Resolve an action token locally and inject the bearer into a child process environment.
| Flag | Type | Default | Description | |------|------|---------|-------------| | --handle | string | | Brokered action token handle | | --actionId | string | gateway | Action id expected by the brokered token | | --scopes | string | | Comma or space separated scopes required for this action | | --env | string | SMITHERS_API_KEY | Environment variable that receives the bearer token | | --command | string | | Shell command to run with the injected token |
Issue a local short-lived Gateway bearer token grant.
| Flag | Type | Default | Description | |------|------|---------|-------------| | --scopes | string | run:read | Comma or space separated Gateway scopes | | --role | string | operator | Role recorded on the token grant | | --userId | string | | User id recorded on the token grant | | --ttl | string | 1h | Token lifetime, such as 15m or 1h | | --actionId | string | gateway | Action id allowed to resolve the brokered action token | | --revealToken | boolean | false | Include the raw bearer token in CLI output |
Revoke a locally issued Gateway bearer token.
| Name | Type | Required | Description | |------|------|----------|-------------| | token | string | yes | Bearer token to revoke |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-14 | fail→pass | 11,161 | 1,336 | -88% | 1 | 1 | 0% | 1,616 | 592 | -63% | 0 | 0 | — |
case-01 | fail→pass | 5,177 | 3,869 | -25% | 1 | 1 | 0% | 812 | 781 | -4% | 0 | 0 | — |
case-02 | fail→pass | 4,560 | 1,972 | -57% | 1 | 1 | 0% | 754 | 750 | -1% | 0 | 0 | — |
case-03 | fail→pass | 6,494 | 1,516 | -77% | 1 | 1 | 0% | 1,037 | 597 | -42% | 0 | 0 | — |
case-04 | fail→pass | 5,905 | 2,114 | -64% | 1 | 1 | 0% | 1,071 | 734 | -31% | 0 | 0 | — |
case-05 | fail→pass | 6,613 | 3,970 | -40% | 1 | 1 | 0% | 1,202 | 754 | -37% | 0 | 0 | — |
case-06 | fail→pass | 7,955 | 3,724 | -53% | 1 | 1 | 0% | 1,316 | 1,099 | -16% | 0 | 0 | — |
case-07 | fail→pass | 15,197 | 2,527 | -83% | 1 | 1 | 0% | 962 | 836 | -13% | 0 | 0 | — |
case-08 | fail→pass | 18,171 | 3,973 | -78% | 1 | 1 | 0% | 3,257 | 1,154 | -65% | 0 | 0 | — |
case-09 | fail→fail | 4,451 | 1,494 | -66% | 1 | 1 | 0% | 681 | 630 | -7% | 0 | 0 | — |
case-10 | fail→pass | 6,434 | 2,065 | -68% | 1 | 1 | 0% | 1,137 | 787 | -31% | 0 | 0 | — |
case-11 | pass→pass | 5,586 | 2,528 | -55% | 1 | 1 | 0% | 1,019 | 719 | -29% | 0 | 0 | — |
case-12 | fail→pass | 7,948 | 1,303 | -84% | 1 | 1 | 0% | 1,246 | 529 | -58% | 0 | 0 | — |
case-13 | fail→pass | 7,208 | 1,315 | -82% | 1 | 1 | 0% | 1,203 | 528 | -56% | 0 | 0 | — |
case-15 | fail→pass | 9,006 | 1,149 | -87% | 1 | 1 | 0% | 1,518 | 527 | -65% | 0 | 0 | — |
case-16 | fail→pass | 9,260 | 1,885 | -80% | 1 | 1 | 0% | 1,390 | 731 | -47% | 0 | 0 | — |
case-17 | pass→pass | 9,259 | 1,997 | -78% | 1 | 1 | 0% | 1,542 | 708 | -54% | 0 | 0 | — |
case-18 | fail→pass | 4,296 | 2,641 | -39% | 1 | 1 | 0% | 653 | 858 | +31% | 0 | 0 | — |
case-19 | pass→pass | 7,124 | 3,754 | -47% | 1 | 1 | 0% | 1,124 | 682 | -39% | 0 | 0 | — |
case-20 | fail→pass | 11,552 | 3,885 | -66% | 1 | 1 | 0% | 2,099 | 785 | -63% | 0 | 0 | — |
case-21 | fail→pass | 8,122 | 3,095 | -62% | 1 | 1 | 0% | 1,240 | 959 | -23% | 0 | 0 | — |
case-22 | pass→pass | 10,272 | 8,619 | -16% | 1 | 1 | 0% | 1,773 | 1,947 | +10% | 0 | 0 | — |
case-23 | pass→pass | 8,429 | 4,791 | -43% | 1 | 1 | 0% | 1,663 | 1,314 | -21% | 0 | 0 | — |
case-24 | pass→pass | 5,788 | 3,096 | -47% | 1 | 1 | 0% | 986 | 923 | -6% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 24 cases were attempted, and 23 counted toward the lift figure. The other 1 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +71 percentage points is the difference between those two pass rates over the 23 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.