Kineti: spend cap, undo, and test proof for AI coding agents
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.
kineti_statusRetrieve current Kineti harness status: active project, locked root goal, current stage, and verification gates.Retrieve current Kineti harness status: active project, locked root goal, current stage, and verification gates.
No input schema was published for this tool.
kineti_lock_goalLock the immutable root goal for the current task run. Fails if goal is already locked.Lock the immutable root goal for the current task run. Fails if goal is already locked.
No input schema was published for this tool.
kineti_set_stageUpdate the active stage or task in the Kineti OS runtime (e.g. 'build', 'spec', 'bugfix', 'refactor', or numbers 1-13).Update the active stage or task in the Kineti OS runtime (e.g. 'build', 'spec', 'bugfix', 'refactor', or numbers 1-13).
No input schema was published for this tool.
kineti_set_gateSet status for a pipeline quality gate ('spec', 'feasibility', 'security', 'audit').Set status for a pipeline quality gate ('spec', 'feasibility', 'security', 'audit').
No input schema was published for this tool.
kineti_evidence_recordExecute a verification test command and record cryptographic SHA-256 fingerprint proof. Takes a command array against an allowlist (bun test, pytest, npm test, project verify). Shell needs human --allow-shell plus TTY.Execute a verification test command and record cryptographic SHA-256 fingerprint proof. Takes a command array against an allowlist (bun test, pytest, npm test, project verify). Shell needs human --allow-shell plus TTY.
No input schema was published for this tool.
kineti_evidence_checkCheck if an existing verification proof is FRESH or STALE against current workspace code.Check if an existing verification proof is FRESH or STALE against current workspace code.
No input schema was published for this tool.
kineti_spend_recordRecord LLM token consumption and enforce stage and task financial circuit breakers.Record LLM token consumption and enforce stage and task financial circuit breakers.
No input schema was published for this tool.
kineti_spend_statusCheck current spend across stages, total task spend, and circuit breaker trip status.Check current spend across stages, total task spend, and circuit breaker trip status.
No input schema was published for this tool.
kineti_saga_pushRegister an undo action on the LIFO rollback stack before executing a state mutation. Takes a command array against an allowlist. Shell needs human --allow-shell plus TTY.Register an undo action on the LIFO rollback stack before executing a state mutation. Takes a command array against an allowlist. Shell needs human --allow-shell plus TTY.
No input schema was published for this tool.
kineti_saga_rollbackRollback uncommitted actions on the LIFO saga stack. Human-only: needs a TTY y/N or explicit --yes; MCP calls fail closed with instructions.Rollback uncommitted actions on the LIFO saga stack. Human-only: needs a TTY y/N or explicit --yes; MCP calls fail closed with instructions.
No input schema was published for this tool.
kineti_verify_gate_statusInspect pre-flight verify gate status and current repository trust.Inspect pre-flight verify gate status and current repository trust.
No input schema was published for this tool.
kineti_egress_recordRecord an outbound network request in the tamper-evident cryptographic egress ledger.Record an outbound network request in the tamper-evident cryptographic egress ledger.
No input schema was published for this tool.
kineti_talkTalk to Kineti in plain words. No skill or command names needed. Handles spending, undo, proof, status, yes/no, on/off, and routes tasks. Always returns plain words plus numbered choices.Talk to Kineti in plain words. No skill or command names needed. Handles spending, undo, proof, status, yes/no, on/off, and routes tasks. Always returns plain words plus numbered choices.
No input schema was published for this tool.
kineti_epistemic_evalprivilegedEvaluate a candidate action against the 360º Human Model (Rule-Exception hierarchies, Epistemic certainty, and Safety ceilings).Evaluate a candidate action against the 360º Human Model (Rule-Exception hierarchies, Epistemic certainty, and Safety ceilings).
No input schema was published for this tool.
14 of 14 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.
Kineti: spend cap, undo, and test proof for AI coding agents
Linked names open Forge’s index of every entry observed exposing that tool. Browse all indexed tools.