Report how many problems the two brains found: mutual review (the other model checks the work, from the peer-review records) and self-check (an agent finds its own error in its own conversation, judged by that agent's own model), side by side. Use when the owner asks whether the second agent or the reviews are worth it, or wants the week's review results.
The English summary is being prepared. Showing the original description.
Run score Not tested
See how to installReview the instructions the agent will receive before you install.
The product claim is two brains: one does the work, another checks it. sno catch-report puts numbers on that
claim from records already on this machine. It changes nothing.
peer-review skill recorded: a different model read the work and
reported problems. sno catch-report run prints those numbers.sno catch-report self reads the
agents' own conversations (~/.claude/projects, ~/.codex/sessions), picks the moments where an agent
reacted to a failing command or test, or admitted a mistake, and asks that agent's own model (claude
judges claude conversations, codex judges codex conversations) whether the agent found the error itself or
was told. It then prints the two side by side.Prerequisites: bash 4+, GNU date, find and grep, and jq. self also needs the claude and/or codex command
line, logged in.
sno catch-report brief --since 7d (or 12h, 30m, 30d, or a
date). It measures both and prints one page: a headline with the problems the second model caught and the moments in which the agents caught their own mistakes (kept apart, never added together), the second brain's
numbers with its biggest catches quoted by title, the agents' own catches in their own words, and how to read
the numbers. Tell the user first that the self-check part sends short excerpts of their conversations to their
own claude or codex (100 by default, about four minutes, it costs tokens); --limit N changes that, and
--agent claude or --agent codex narrows it. --agent cursor reads Cursor's conversations
(~/.cursor/projects/*/agent-transcripts) instead and has cursor-agent judge them; Cursor transcripts hold no
tool output, so only its spoken admissions count there, and no per-message times, so a Cursor conversation updated in
the period counts with its whole history.--limit, and only sees errors an agent said
out loud within ten steps of a failure or in a known admission phrase (English and Chinese); quiet fixes are
not seen.sno catch-report run prints the review records (reviews started, finished,
refused and never finished; per reviewer model the high and medium findings and fix-now; verdicts;
the five reviews with the most fix-now; findings the owner has ruled on), and sno catch-report self --list
prints each self-check moment with the model's verdict. Both take --stats FILE and --findings FILE for
records kept elsewhere. The records are ~/.local/state/codex-review-stats.jsonl and
~/.local/state/codex-reviews/findings.jsonl.review-findings.sh set <id> accepted|rejected|superseded (the peer-review skill); this command never
rules on anything.No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Answer how long agent work will take, how much longer active work needs, or what clock time applies. Estimate full AI-agent wall time, measure active progress first, and get owner-facing times from `sno report-time`. Never estimate human-developer time.
The English summary is being prepared. Showing the original description.
Prove that a reported run caused its intended real effect. Walk the executor path from entry to effect, capture one observable per hop, and report a result a no-op could not produce.
The English summary is being prepared. Showing the original description.
Give the owner one page when they come back from sleep, a meeting or a long run: what got done, what is stuck, what waits for their answer, and what it cost in quota. Use when the owner asks what happened while they were away, wants a status page, or when you finish a long stretch of work and must report it.
The English summary is being prepared. Showing the original description.
Write, revise or review a charter: the one document that tells an executor what to deliver, what is out of bounds, what the owner already decided, and how each success check will be proven. Use when work needs a written brief before someone else does it, or when asked to write, change or check a charter.
The English summary is being prepared. Showing the original description.
MANUAL-ONLY: load solely when the human owner types `/cos`, uses `$cos`, or asks you to act as the Chief of Staff (COS). The COS is the one agent the owner talks to; it coordinates the owner and the per-project Project Leads (PLs). A task card, charter, or dispatch makes you an executor, not COS.
The English summary is being prepared. Showing the original description.
Turn repeated management failures into enforced COS or PL rules. Load ONLY after the owner has explicitly activated the cos role for this session and the COS core routes here. Never invoke directly.
The English summary is being prepared. Showing the original description.