Sidecrew

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/lvlrsajjad-sidecrew

About

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools

7 read · 2 write · 0 delete · 4 not yet classified

Secrets

None asked for

Install scripts

Not scanned yet

Runs as

Node.js package

Tools (13)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

• sidecrew_escalate

  What the local workers could not do, assembled for you to write yourself. Reads .sidecrew/runs/<id>/escalations.jsonl and returns each failed task with the exemplar and rules the worker had, plus both attempts' errors. Costs no worker tokens — it reads a finished run off disk. Two failures in here are NOT the test's fault and must not be rewritten as though they were: a stage_reached of 'mutation' means the mutation tool broke, and four mutation counts of zero mean nothing in that function could be mutated.

• sidecrew_fix

  Run a whole change plan on this machine: workload #2a, behaviour-preserving changes — type errors, renames, null guards, API migrations, dead code. For each task the local model rewrites the listed files whole, and a gate a machine can run decides what you see: the diff stayed confined to the task's files, tsc is clean in them with none introduced elsewhere, and every test that passed before still passes. Generation is local and costs zero Claude tokens; only the FixResult comes back, so you see survivors and escalations rather than raw worker output. SLOW — the project's own suite runs per ca…

• sidecrew_fix_escalate

  What the local workers could not change, assembled for you to do yourself. Reads a fix run's escalations.jsonl and returns each failed task with the files it was given and every attempt's verdict — which confinement rule fired, which tsc errors remain, which tests regressed. Costs no worker tokens; it reads a finished run off disk. TWO of these are NOT the worker's fault and must not be rewritten as though they were: machine_failure means the sandbox or the runner broke (exclude it from any rate you quote), and a non-null `refused` means the worker said the change cannot be made inside those f…

• sidecrew_fix_plan_validate

  Check a change_plan.json before a run spends anything on it, and REFUSE the tasks no worker could ever pass: a file too large to return whole (a worker rewrites whole files, so ~8k completion tokens is the ceiling), a pre-existing tsc error the ask does not cover (the gate requires zero errors in the task's own files, so such a task is unsatisfiable at any temperature), a file outside the tsconfig's program, two tasks in one step sharing a file. Call it after writing or editing a plan. The expensive half is a real tsc over the project — tens of seconds — and it is the half that produces the re…

• sidecrew_generate

  One WorkerTask -> one candidate test, generated by the MLX model running on this machine. Costs zero Claude tokens and touches no network: it is an HTTP call to http://localhost:<port>/v1. Raw worker output — verify it before showing it to anyone.

• sidecrew_plan_validate

  Check a test_plan.json before a run spends anything on it: it parses, its module and exemplars are on disk, every line range really is the function it names, and — unless verify_exemplars is false — every exemplar survives the verifier. Call it after writing or editing a plan. Verifying the exemplars is the expensive half: one verdict per shape, seconds on TypeScript and tens of seconds on Swift. A stale source_sha is a warning here and a refusal in sidecrew_run_batch.

• sidecrew_query

  Predicate questions about a TypeScript project, answered by its own compiler instead of by you reading files: `refs` (who references a declaration — the compiler's references, not a grep's), `unreferenced` (exports nothing outside their own file uses, with decorated classes marked because reflection is invisible to a reference count), `sizes` (which files fit a whole-file rewrite and how many of a too-big file's declarations fit as symbol tasks), `diagnostics` (where the errors are, and with a flag only what the flag adds). Use it while planning instead of writing grep or analysis scripts: tha…

• sidecrew_read

  Ask the local worker to read up to 10 files and answer one question — "which of these handle retries", "what does this module do on a missing record" — instead of reading them yourself. Only claims whose EVERY quote a machine found byte-for-byte inside the lines they cite come back, each with file:lines; invented or paraphrased evidence is dropped and only counted. Admitted means the evidence exists, NOT that the claim is relevant or complete: open the cited lines before you act on anything load-bearing, and treat nothing_found as 'read it yourself', never as 'absent'. Runs on this machine, ze…

• sidecrew_recon

  How many TypeScript errors a project has under its own configuration, and how many each stricter compiler flag would add — split into source files and test files, with the worst files and the commonest error codes. Answers "how many TypeScript issues are there?" completely, and is the report to put in front of the user before planning a strictness migration: "your config reports 0, --strictNullChecks reports 763 — do you want to see them?". Runs the project's own tsc in a copy of the project on this machine: no worker, no network, and zero Claude tokens beyond reading the report. A minute or m…

• sidecrew_review

  Which survivors are worth reading, and in what batches. Survival is a filter, not an endorsement — a test that pins today's wrong answer kills every mutant — so this returns survivors below the mutation-score threshold plus a deterministic audit sample of the rest, batched under a token cap. The threshold is per language and defaults accordingly: a Swift score is computed over one or two mutants against TypeScript's six to twelve. Reads a finished run off disk; no worker tokens.

• sidecrew_run_batch

  Run a whole plan on this machine: for every function x shape, generate -> verify -> retry once with the error appended -> escalate. Generation is local and costs zero Claude tokens; only the BatchResult comes back, so you see survivors and escalations rather than raw worker output. Minutes, not seconds — roughly 10 s per TypeScript candidate and 40 s per Swift one.

• sidecrew_status

  Is a local worker up, which model and revision it is serving, free RAM, and which verifier tools this project has. Call it before a run: everything else here needs a worker, and a missing stryker or muter is why a verdict would fail for a reason that is not the test's fault.

• sidecrew_verify

  compile -> run -> mutate one candidate against the function its task_id names, and return a Verdict. Survive means it compiled, passed against the unmodified source, killed at least one mutant of that function, and was not tautological. Runs entirely on this machine.

Signals

Stars

0

Forks

0

Open issues

0

Last commit

Sep 25, 2026 (1 month ago)

Last release

Sep 24, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

Registry name

io.github.lvlrSajjad/sidecrew

Version

0.2.0

Auth

No auth

Packages

npm sidecrew

License

MIT

Repository

github.com/lvlrSajjad/sidecrew

First seen

Oct 24, 2026

Last checked

Oct 24, 2026

Source

Official MCP Registrygithub-graphql