The developer index now has two surfaces, the same as research: the
`developer` category on `firecrawl search`, and a dedicated command.
The command mirrors the research commands. It calls GET
/v2/developer/search, keeps the keyless free-tier path, and renders the
ranked hits as markdown blocks with the passages clipped at 1200
characters; `--json` keeps the full envelope. It takes a query and
`--limit` only; the endpoint accepts no filters, and that narrow
surface is deliberate.
New tests cover the request URL, the readable and JSON output, and the
error path. Two argv tests prove the command appears in the root help
and parses, so a wrapper cannot drop it the way `executeSearch` once
dropped the category group.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01C4vZ6XH65bUJDkLthyfmvC
`firecrawl search <query> --categories developer` searches an index built
for coding agents: GitHub issues, merged pull requests, repository
READMEs, and curated documentation sites.
The API already served the category. The CLI rejected the value, and
`executeSearch` copied only `web`, `images`, and `news` out of the
payload. A developer group therefore never reached the caller.
The category is an extra arm, not a filter on the web results, so the API
returns its hits in `data.developer`. The command copies that group
through, prints it under its own heading, and labels the web group when
both are present.
A matched passage runs to several KB. The readable output clips it at 500
characters and names `--json`, which keeps the full text. Without the
clip, three hits flood a terminal.
Validated in the Stage-1 final canary: CLI config stores an environment reference, not a literal credential; production MCP compatibility remains green.
Add support for scoping init/setup to a single agent/harness. README documents one-shot usage. scripts/install.sh forwards installer args to `firecrawl init` (non-interactive) and runs `init --yes` when piped. init.ts: add interactive harness picker, detectInstalledAgentNames, and installRepoAcrossAgents to allow routing skills/workflows to a subset of detected agents or a single --agent. skills-native.ts: canonicalize per-agent global skills dirs (fixes several agent paths), add detectInstalledAgentNames helper. This enables one-shot, non-interactive, and interactive per-harness installs.
Research commands bypassed the SDK's typed methods and never set
integration, so requests were logged with integration=NULL. Append
integration=cli as a query param in getResearch, covering all five
subcommands in both keyed and keyless modes. Bump to 1.19.24.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BJ3prpziToFecBhLGRiX6t
Allow monitor create/update to only read piped stdin when flags can't build a payload. Added allowImplicitStdin option to readJsonPayload and exported helpers hasCreateFlagPayload / hasUpdateFlagPayload to detect when flags are sufficient. Updated command actions to pass the allowImplicitStdin flag and extended tests to cover the stdin payload policy. Also bumped package version to 1.19.23.
- monitor create --help: a 'Target modes' section distinguishing single page,
URL batch, whole-site crawl, and web-search targets.
- On create, print the Cloud dashboard link + a run-now hint (interactive only,
so pipes/--output stay clean).
- SKILL.md: a target-mode table so agents pick the right flags.
- Bump version to 1.19.21.
Clarify messaging by changing references from 'search monitors' to 'web monitors'. Update the thrown error in buildCreateBody to "--goal is required for web monitors (--queries)" and adjust the corresponding unit test to expect the new wording. This makes it clearer that a goal is required when creating web monitors with queries (the API auto-enables the AI judge). Files modified: src/commands/monitor.ts, src/__tests__/commands/monitor.test.ts.
Search monitors (type:"search") are implemented in the API but undocumented.
Add --queries/--search-window/--max-results/--include-domains/--exclude-domains
flags, build the search target in buildCreateBody, and require --goal for search
monitors (the API mandates a non-empty goal). Includes tests.
The installed CLI skill stated agents must authenticate first, which
does not match the code: search, scrape, and interact already work
without an API key. Add a keyless free-tier fallback note while keeping
browser login and API key as the preferred setup.
Add native skills installation support and an interactive setup picker for launch flow. Introduces nativeSkills and quiet options, colorized/condensed output, and status summaries from the native installer (skills-native.ts). The launch command can now prompt to install MCP, skills, or both, and passes ALL_SKILL_REPOS to the skills installer; MCP/skills installs now run with quiet/native flags by default when appropriate (launch.ts, setup.ts). Tests updated to mock inquirer select, handle TTY changes, and assert the new behavior. Also remove the implicit default for the --yes launch option in the CLI (index.ts).
The notice wraps "Update available!" in ANSI codes on a TTY, so the
contiguous substring assertion failed in CI. Assert on the version
portion that survives colorization instead.
Claude-Session: https://claude.ai/code/session_016Szz5ZgWNULKbvNGqt8sdm
Add a skillsAgent property to several LaunchTarget entries (claude-code, codex, codex-app, opencode) so the launcher can associate skill installation with the correct agent. Update unit tests to assert installSkillsForAgent is called (or not called) where appropriate and add a test to verify skipping skills for opencode. Adjusted expectations/counts in existing tests to reflect the new behavior.
Bump CLI version and add YAML dependency; implement native MCP installers for Hermes and OpenClaw and a hosted Firecrawl MCP URL. Normalize agent aliases and extend setup/installMcp to handle special launchers (hermes, openclaw, and --agent all) and to invoke add-mcp with the hosted MCP URL and transport option. Add functions to write Hermes config and configure OpenClaw via its CLI, and add installSkillsForAgent helper. Extend launch command to recognize hermes/openclaw targets, run their MCP installers, optionally install skills (new --skip-skills flag), and launch with correct args. Update command help text and expand tests to cover these new behaviors.
Kris Oei