Skip to content

MantaDigital/stingray-agent-skills / skills/stingray

stingray

Verified

Trading strategy builder for coding agents. Use when Codex, Claude, Cursor, or a SKILL.md host needs to turn a trading idea into market Evidence, an inspectable Signal, a private Replay, Replay status, or an opt-in Studio Publication. Stingray does not place trades.

references/token-lifecycle.md

View on GitHub
# Token Lifecycle

Read this file when explaining token setup, scope, storage, or revocation.

## Token Model

- Token prefix: `sa_pat_`
- Required public skill scope: `skills:full`
- Preferred local env var: `STINGRAY_PAT`
- Optional local file: `~/.stingray/credentials`
- Plaintext tokens are shown only once by the provisioning flow.
- Tokens remain valid until revoked.

## Creation

Token creation is not exposed through the public skill. Studio Skills API tokens
are currently provisioned for the private-beta Skills API surface. Ask the user
to get a `skills:full` token from their Stingray contact or current provisioning
flow.

Do not try to create a token from an API-token-authenticated agent. Do not ask
the user to paste the token into chat.

## Local Storage

The agent may give the user a terminal command that writes:

```text
STINGRAY_PAT=<token>
```

to `~/.stingray/credentials` with mode 600, or the user may place the token in
their shell environment. The secret stays in their terminal.

## Revocation

Use the current Stingray provisioning flow to revoke or rotate Studio Skills API
tokens. If future public Skills API token-management actions or browser UI are
added, update this file. For now, do not advertise token list or revoke API
routes as part of the public skill surface.

## Scope Failure

If a token exists but the API returns insufficient scope, tell the user to create
or update a token with `skills:full`.

Do not include token ids, raw token values, last-four metadata, or source
metadata in chat, debug reports, Linear, Slack, PRs, or logs.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall