Hands bounded coding work to cheaper worker agents: verified answers, exact diffs, cost receipts.
Inferred from the transports this listing declares (stdio). A client not listed here hasn’t been ruled out — it just isn’t something Forge can confirm.
Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts.
Read out of the source npm actually ships, at scan time. The package was never executed. Tools registered dynamically at runtime, or hidden inside bundled or minified code, can be missed — so this is a floor on the tool surface, not a complete census of it.
run-reportThe report of a run: answer, receipt, verified references.The report of a run: answer, receipt, verified references.
No input schema was published for this tool.
run-patchprivilegedThe exact diff an isolated or in-place run made.The exact diff an isolated or in-place run made.
No input schema was published for this tool.
researchFind, map or explain code through a read-only worker, and verify what comes back.Find, map or explain code through a read-only worker, and verify what comes back.
No input schema was published for this tool.
questionWhat to find out about the project.What to find out about the project.
No input schema was published for this tool.
implementA worker makes a change in an isolated copy; you review the exact diff and apply it only when it is right.A worker makes a change in an isolated copy; you review the exact diff and apply it only when it is right.
No input schema was published for this tool.
taskThe change to make, with the context a worker needs.The change to make, with the context a worker needs.
No input schema was published for this tool.
reviewA read-only reviewer from another model judges a commit range or the latest change.A read-only reviewer from another model judges a commit range or the latest change.
No input schema was published for this tool.
rangeA commit range such as main..HEAD. Default: the latest run's change.A commit range such as main..HEAD. Default: the latest run's change.
No input schema was published for this tool.
crewIndependent tasks run in parallel as one group of workers.Independent tasks run in parallel as one group of workers.
No input schema was published for this tool.
tasksThe tasks, one per line.The tasks, one per line.
No input schema was published for this tool.
pitroom_runNo description publishedThis tool published no description. Forge does not invent one.
pitroom_waitWait for runs that came back "still running" and return their reports.Wait for runs that came back "still running" and return their reports.
No input schema was published for this tool.
pitroom_showA run's report (live progress while it runs); patch: the exact diff; full: the untruncated answer.A run's report (live progress while it runs); patch: the exact diff; full: the untruncated answer.
No input schema was published for this tool.
pitroom_infoReports, changing nothing. topic: runs (latest runs; running, group), history (search earlier answers before asking again; text, state, model, since, limit), stats (success rate, time, tokens, audits per worker; since), savings (since, perModel), models (a backend's models and costs; worker, all),…Reports, changing nothing. topic: runs (latest runs; running, group), history (search earlier answers before asking again; text, state, model, since, limit), stats (success rate, time, tokens, audits per worker; since), savings (since, perModel), models (a backend's models and costs; worker, all),…
No input schema was published for this tool.
pitroom_reviewA read-only reviewer (another worker by default) judges a run's change or a commit range ("main..HEAD"): findings with severities and a SPEC / QUALITY verdict.A read-only reviewer (another worker by default) judges a run's change or a commit range ("main..HEAD"): findings with severities and a SPEC / QUALITY verdict.
No input schema was published for this tool.
pitroom_auditAnother worker re-checks a read run's answer: AGREE, PARTIAL or DISAGREE, with the disputed claims.Another worker re-checks a read run's answer: AGREE, PARTIAL or DISAGREE, with the disputed claims.
No input schema was published for this tool.
pitroom_applyLand an isolated run's patch (or a group's, in order) on the working tree; checked first. A patch deleting files needs allowDelete: pass it only after checking the deletions were asked for.Land an isolated run's patch (or a group's, in order) on the working tree; checked first. A patch deleting files needs allowDelete: pass it only after checking the deletions were asked for.
No input schema was published for this tool.
pitroom_discardDrop an isolated run's private copy (the patch is kept).Drop an isolated run's private copy (the patch is kept).
No input schema was published for this tool.
pitroom_revertUndo a mode "write" run's changes (refused if the files changed since).Undo a mode "write" run's changes (refused if the files changed since).
No input schema was published for this tool.
pitroom_stopStop a running or queued run, or a group; cooldowns: try rate-limited models again now.Stop a running or queued run, or a group; cooldowns: try rate-limited models again now.
No input schema was published for this tool.
pitroomNo description publishedThis tool published no description. Forge does not invent one.
19 of 21 tools published a description.
Tool names and descriptions are written by the publisher and shown verbatim as inert text. They are the strings an MCP client passes to a model, so Forge scans them for prompt-injection patterns — any finding appears with the security scan above. “Privileged” is a keyword match on the tool name, not an audit of what the tool does: a benign-sounding name can still do anything.
Hands bounded coding work to cheaper worker agents: verified answers, exact diffs, cost receipts.
Linked names open Forge’s index of every entry observed exposing that tool. Browse all indexed tools.