catch-report — Claude Code skill: review stats
The catch-report Claude Code skill compares findings from peer reviews with mistakes agents catch themselves. It runs when someone asks for review results or a weekly summary.
Apache-2.0 ★ 869 updated 2026-11-16
npx skills add sno-ai/sno-station-skills --skill catch-report -a claude-codeWhat catch-report does
catch-report gathers figures from peer-review records and agent conversations, then presents the two kinds of findings side by side. Mutual review counts issues reported by another model; self-check looks for moments when an agent recognized its own error. Run sno catch-report brief --since 7d for a period summary or sno catch-report run for review statistics.
Self-check sends short conversation excerpts to the agent’s Claude or Codex model for assessment, which uses tokens; the default sample is 100 moments. It requires an authenticated claude and/or codex command. Bash 4+, GNU date, find, grep, and jq are also required. The skill reads records without changing them.
What it helps with
- compare issues found by a second model with agents’ own catches
- summarize review results for a chosen period
- inspect reviews that were completed, refused, or left unfinished
- list self-check moments with model verdicts
Example prompts for the agent
- Compare peer-review findings with mistakes agents caught themselves this week.
- Show review results from the last
30d. - List the moments when an agent noticed its own error.
How to install catch-report
1Skills CLI (Vercel)
npx skills add sno-ai/sno-station-skills --skill catch-report -a claude-code2Manually: put the files in place
~/.claude/skills/skill/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/skill/
1Skills CLI (Vercel)
npx skills add sno-ai/sno-station-skills --skill catch-report -a codex2Manually: put the files in place
.agents/skills/skill/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add sno-ai/sno-station-skills --skill catch-report -a cursor2Manually: put the files in place
.cursor/skills/skill/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install sno-ai/sno-station-skills skills/H-reporting-and-visibility/catch-report/skill2Manually: put the files in place
.github/skills/skill/SKILL.md1Skills CLI (Vercel)
npx skills add sno-ai/sno-station-skills --skill catch-report -a gemini-cli2Platform CLI
gemini skills install https://github.com/sno-ai/sno-station-skills --path skills/H-reporting-and-visibility/catch-report/skillManually: put the files in place
.devin/skills/skill/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add sno-ai/sno-station-skills --skill catch-report -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about catch-report
How do I install catch-report in Claude Code?
Run npx skills add sno-ai/sno-station-skills --skill catch-report -a claude-code. The skill file is placed at ~/.claude/skills/skill/SKILL.md.
What does catch-report do?
It compares findings recorded by the peer-review skill with cases where an agent recognized an error in its own conversation. Use sno catch-report run for review details or sno catch-report self --list for self-check moments.
What does catch-report need to run?
It requires Bash 4+, GNU date, find, grep, and jq. Self-check also needs an authenticated claude and/or codex command, and uses tokens.
Source text
SKILL.md · Apache-2.0
---
name: catch-report
description: "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."
requires:
programs: []
harness:
- {slot: 4.shell, need: required}
- {slot: 4.file-read-write, need: required}
---
# catch-report
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.
- **Mutual review** is every review the `peer-review` skill recorded: a different model read the work and
reported problems. `sno catch-report run` prints those numbers.
- **Self-check** is an agent finding its own error inside one conversation. `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.
## Use
1. To show the user what the two brains caught, run `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.
2. Hand the page to the user as printed, headline first, in English: do not translate it or re-word it. Keep every number and the plausible range exactly as
printed, keep the quotes, and keep the "How to read this" notes. Do not round up, do not add a claim the page
does not make, and do not say the findings are "real problems" or whose work was wrong: the records hold no
author and most findings are undecided. You may add one sentence on what stands out.
3. When the page says the self-check could not be measured, say that; do not report a zero. The self-check count
is an estimate from a sample when there are more moments than `--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.
4. For the details behind a number: `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`.
5. To make the ruled column mean something, rule on findings with
`review-findings.sh set <id> accepted|rejected|superseded` (the `peer-review` skill); this command never
rules on anything.
© sno-ai · Apache-2.0 · sno-ai/sno-station-skills