What does runtrim finish do?
It evaluates the run against the defined task, checks changed file paths against allowed scope, and surfaces verification debt and missing proof with a PASS / WARN / BLOCKED verdict.
Run verification
Verify what AI coding agents changed before shipping.
AI agents report completion without a structured verification step. RunTrim checks changed files, scope adherence, and missing proof after the run so risky output does not ship unreviewed.
Claude CodeCursorCodex CLIChatGPT
01 / The problem
What goes wrong
- AI coding agents report completion but changed files are not always verified.
- Scope drift goes undetected until a diff review or a production incident.
- Verification debt accumulates silently across multiple sessions.
02 / Root cause
Why this happens
- Agent UIs surface conversation output, not a structured list of changed paths.
- Engineers move fast and skip manual diff review under time pressure.
- Without a defined verification step, completion is assumed rather than confirmed.
03 / Without RunTrim
Manual workaround
- 1Run git diff after each agent session and manually review every changed file.
- 2Compare changes against original task intent to identify scope violations.
- 3Document missing proof and unresolved checks before moving to the next task.
04 / With RunTrim
RunTrim workflow
runtrim
local
$runtrim start
$runtrim agent "your task" --copy
$runtrim finish
Privacy and trust
- Source code stays local. RunTrim never uploads it.
- No account required for the free CLI.
- RunTrim tracks changed file paths, run status, verification debt, and local memory.
- Cloud sync is optional and metadata-only.
05 / FAQ
Common questions
What is verification debt?
Verification debt is the accumulated set of checks and confirmations that were defined before the run but not yet confirmed as passing after it.
Does RunTrim run tests automatically?
No. RunTrim tracks which verifications were defined and which are still outstanding. Running the actual tests is the engineer's responsibility.
What does runtrim report produce?
A structured summary of the run including status, changed paths, risk indicators, verification debt, and recommended follow-up actions.
Does RunTrim read file contents?
RunTrim reads changed file paths and project config locally. It does not read file contents or upload source code.
Related resources
Keep AI coding agents scoped before they edit.
Broad tasks can drift into auth, billing, env, database, middleware, and other sensitive areas. Guardrails reduce that risk.
Keep run history across Claude, Codex, Cursor and ChatGPT.
AI coding gets messy when every session starts from scratch. RunTrim keeps local run memory visible between sessions.
AI agent scope drift: what it is and how to prevent it.
Scope drift happens when an AI coding agent edits files outside the intended task surface. It costs tokens, introduces risk, and makes post-run review harder.
Reduce Claude Code token waste with scoped runs and local memory.
Token waste in Claude Code comes from unscoped tasks, repeated context reconstruction, and sessions that restart from scratch after a limit. RunTrim addresses all three.
Check what actually changed
Run runtrim finish after every agent session to surface scope violations and verification debt before they ship.
terminal
$npm install -g runtrim
$runtrim start
$runtrim agent "your task" --copy
Free · No account required · Local-first · Agent-agnostic