London Dávila
d58743b5eb
doctor still described `schema_version` 1 and 2 + bailed above 2, but CLI emitted 3 since 0.22.0 and skill pins `@tiny-fish/cli@latest`. as shipped it degraded to `--pretty` on every run. The feedback skill also passed an unquoted, user-derived title to `gh issue create`. three fixes landed in tinyfish-web-agent-integrations#29; this keeps the two copies of the plugin textually identical - `doctor`: schema 3 — `cli_version`, `ok_harnesses`/`ok_cli`, `checks[].scope`, `repairs[].action`, and the exit code coming from the harness scope alone, so `ok_cli: false` beside exit `0` is a real state. Drops the `registered, API key present but unverified` string the CLI no longer emits; `--fix` examples run through `npx` like step 1. - `feedback`: `--title "$title" --body-file "$body_file"`, injection warning widened to the title, and `eval` / constructed command strings prohibited. - `plugins/tinyfish/README.md`: adds `~/.grok` to the config dirs doctor reads, per the CLI's `CONFIG_DIRS`. The rest of that list matches. - 1.2.3 → 1.2.4 in `plugin.json` and the marketplace entry — `validate-skills.mjs` fails if they diverge --------- Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
TinyFish
The complete web toolkit for your agent — search, fetch, browser automation, and headless browser control.
Skills
search, fetch, and agent are built on TinyFish's hosted MCP server (bundled via .mcp.json). No install, no CLI needed — first use triggers an OAuth sign-in to your TinyFish account (requires an account with available credits). They work in any environment, including sandboxed surfaces without terminal access.
/tinyfish:search— free, token-efficient web search with flexible recency/date filtering and news/research-paper scoping/tinyfish:fetch— free, clean content extraction from up to 10 URLs in parallel, including JS-heavy pages/tinyfish:agent— browser automation (600 free automation credits for new users, then your plan's credits): natural-language goals, batch runs across multiple sites, and raw CDP browser sessions
The remaining two are setup tools rather than web tools, and both use your terminal:
/tinyfish:doctor— diagnose and repair your TinyFish setup. Runs the TinyFish CLI (npx @tiny-fish/cli doctor) for the config checks, then calls a TinyFish tool to prove this agent can actually reach the service. Without a terminal it still runs that second half./tinyfish:feedback— file a bug report or a doctor diagnostic as a GitHub issue on the publictinyfish-io/tinyfish-cookbookrepo, viagh. Nothing is sent until you approve the exact text.
Desktop setup note
In Claude Desktop, installing this plugin enables its skills but the bundled tinyfish MCP connector still needs one manual step: open the plugin's Connectors tab and click Install on tinyfish before the skills can actually call it.
Privacy
TinyFish's privacy policy: https://www.tinyfish.ai/privacy-policy
Local file access
search, fetch, and agent read no local files — every operation goes through the TinyFish MCP server.
The two setup skills do touch your machine:
/tinyfish:doctorruns the TinyFish CLI, which reads your agent config directories (~/.claude,~/.codex,~/.cursor,~/.grok,~/.hermes,~/.openclaw,~/.config/opencode) and the CLI credential store (~/.tinyfish/config.json) to find where TinyFish is registered. Diagnosis reads those files and makes authenticated calls to TinyFish to test what it found; the repair step rewrites the registrations, and only commands the CLI itself proposes.doctorreports its own run to TinyFish — setTINYFISH_NO_TELEMETRYto suppress that and thetinyfish connecta repair re-runs./tinyfish:feedbackshells out togh issue createagainst a public repo, after showing you the exact issue text and waiting for your approval.