Extcord

Quality 76 / 100good

11 tools, about 5,225 tokens to load them all · tool set 38fe57a4873d · tools last changed 2026-10-11 · checked 2026-10-20 09:31 UTC

Tool changes

• 2026-10-11inspectremoved

  Look at a handle: its summary, its value one page at a time, or its provenance. Check est_tokens in the summary before reading a big value; it's usually cheaper to narrow it with an op first (find, select, filter, fit).

• 2026-10-11discoverremoved

  Find the right op or recipe for a job. With query: the best matches, led by recipes other agents already proved ("solved_before"). With op: that op's full contract and examples. With no arguments: every op by category with a one-line intent. To read everything at once, use the resource extcord://catalog.

• 2026-10-11package_inforemoved

  A package's latest version, release date, license, Python or Node requirement, summary and links, in one call. The raw registry response this replaces can run to hundreds of thousands of tokens (numpy's PyPI JSON is about 900,000); this answer is about 150. Example: package_info(ecosystem="pypi", name="numpy").

• 2026-10-11datesremoved

  Dates and times done right: models don't know today's date and slip on calendar math; this is exact and DST-aware. now: current date and time in any zone. add: add or subtract days, months (month ends handled) or business days. between: days, weeks, years/months/days and business days between two dates. info: weekday, week number, time zone conversion. e.g. dates(action="add", date="2026-10-07", add={"business_days": 10}).

• 2026-10-11calculateremoved

  Exact arithmetic with no floating-point surprises: 0.1 + 0.2 = 0.3, money strings read as numbers, round half-up, percentages (pct, pct_change), sqrt, sum, mean, median, min, max, comparisons. Use it instead of doing math in your head. Example: calculate(expr="price * qty * (1 + tax/100)", vars={"price": "$19.99", "qty": 3, "tax": 8.25}, places=2) gives 64.92.

• 2026-10-11invokeremoved

  Run any of the 43 ops by id. data: json_parse, get, filter, pick, pluck, sort, unique, count_by, stats; format: to_markdown, to_csv, to_text, join, template; compute: calc, now, date_info, date_add, date_diff, encode, decode, url_parse, validate; html: html_clean, html_to_text, select, extract_links, extract_tables, extract_meta; structure: outline; network: fetch; text: find, contains, slice, fit, chunk, replace, split, regex_extract, normalize, count, diff; integrity: hash. discover(op=<id>) shows an op's args and examples. The result comes back as a handle: the value itself if small, else a preview you can pass to the next op. Example: invoke(op="html_to_text", input="h_...") or invoke(op="json_parse", input="{'a': 1,}", args={"lenient": true}).

• 2026-10-11delete_recipeadded

  Permanently delete a recipe you saved, with its version history and track record, using the edit_key from its first save. Use this to withdraw a recipe that's wrong or no longer needed; to change one, publish a new version with save_recipe and the same key instead. Other agents can no longer run it. Recipes that repaired it stay published and are listed in the reply. The name is retired, never reused, so anyone who refers to it gets a clear 'deleted' error rather than a different pipeline. Built-in recipes can't be deleted; a wrong key, or a name that doesn't match exactly, returns an error and changes nothing.

• 2026-10-11save_recipechangeddescription, input schema, output schema, annotationsmeaning changed
  before

  Give a working pipeline to the commons so any agent can reuse it with run_recipe. With an example it's verified before it's accepted; with expect its track record reflects correct results, not just non-crashing ones. Returns an edit key (keep it) for publishing new versions later.

  after · 20% of words in common

  Publish a pipeline that worked as a public recipe any agent can run with run_recipe, or publish a new version of one you saved before (pass its edit_key). With an example, the recipe is run once (this fetches live pages, counting toward your fetch limit) and only published if it runs without error and meets expect (with no expect, running without error is the test); without an example it's published as unverified. A new version that fails verification is refused and the current version stays live. Recipes are public: never put secrets, personal data or private URLs in steps or examples. The first save returns an edit_key, shown once and not recoverable: keep it to publish versions or delete_recipe later (without it, a recipe can only be superseded by a repair). To fix someone else's broken recipe, save yours under a new name with repairs=<their name>; discover_ops(query=...) then lists yours first. Limited to 10 saves an hour per client; a taken name, a bad key or a failed verification returns the reason and fix.

• 2026-10-11run_recipechangeddescription, input schema, output schemameaning changed
  before

  Run a recipe from the commons in one call. Its result is checked against the recipe's expectations, and the outcome feeds its track record. Built-ins include pypi_package, npm_package and crate_info (package facts), github_readme_outline, page_to_markdown, page_outline, page_links, page_tables and find_on_page.

  after · 16% of words in common

  Run a saved recipe (a named, parameterized pipeline, built in or published by agents) in one call; its result is checked against the recipe's expectations. version runs an earlier version from its history, checked against that version's own expect and recorded on that version. Use this when discover_ops lists a recipe for your job (see solved_before); for single pages and package lookups use read_page and read_package_info, which run the built-in recipes for you, and for your own one-off chain use run_pipeline. params must match the recipe's declared params (see discover_ops(recipe=<name>)); defaults can be left out, and missing or unknown params return the param list. verified.correct=false means it ran but the result looks wrong (often a site changed): verified.advice names any repaired recipe. Each real run is recorded in the recipe's public run statistics (success rate, agents using it); only runs with the recipe's own example can mark it broken. dry_run runs and records nothing. Recipes that fetch count toward 60 fetches a minute. An unknown name returns a did-you-mean.

• 2026-10-11read_handleadded

  Read a stored result (handle) without running anything: view=summary for its type, size, est_tokens and suggested next ops; view=value for the data itself one page at a time (follow next_offset); view=provenance for the ops, args and source URLs that produced it. Use this when a result came back as a preview and you need more of it. Check est_tokens first: for a large value it's usually cheaper to narrow it with run_op (find, select, filter, fit) than to page through it. Handles expire 60 minutes after they're made; an expired or unknown id returns handle_not_found with a suggestion to re-run the step.

Showing the latest 10. Full history: list_changes · trend: quality JSON.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.