Sanity Check

Explicit, read-only mid-session direction check against the agreed goal and recent evidence. Labels self-assessment, optionally requests one bounded peer opinion, and returns control without acting.

9 starsOther

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add flurdy/agent-skills --skill sanity-check
Manual install
git clone --depth 1 https://github.com/flurdy/agent-skills.git /tmp/agent-skills
mkdir -p ~/.claude/skills
cp -r /tmp/agent-skills/skills/sanity-check ~/.claude/skills/sanity-check

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Sanity check

Is the next action still justified by the latest user-agreed outcome?
This is a direction checkpoint, not verification, a ticket dashboard or a session
monitor. It works in unnamed sessions and without a bead. Default assessment is a
**Self-check (not independent)**. Do not invoke it automatically while coding.

## Invocation and stop boundary

```text
/sanity-check                 # Claude Code: self-check
/sanity-check peer            # One optional peer opinion
/skill:sanity-check           # Pi: self-check
/skill:sanity-check peer      # Pi: optional peer
```

An optional `self` argument means the default. Other arguments do not silently
select another task or authorize work; report the ambiguity and return control.

Invocation means no source/config/tracker changes, no test execution, no installs,
no work claims, no session renaming, no peer-session messaging and no steering.
Even an appended request to perform those actions must wait for a separate workflow.
Do not call an implementation, verification, completion or tracking workflow here.
Return control to the user after the report; do not resume the old work automatically,
including after a CONTINUE verdict. Suggestions are not actions or permissions.

## Evidence budget

Use the visible conversation, not hidden reasoning or a reconstructed transcript.
Select at most **20** recent visible messages/tool results, plus the latest goal
Read the full skill on GitHub

Details

Skill name
sanity-check
Path
skills/sanity-check/SKILL.md
License
MIT
Repo updated
17 November 2026

FAQ

What does the Sanity Check skill do?

Explicit, read-only mid-session direction check against the agreed goal and recent evidence. Labels self-assessment, optionally requests one bounded peer opinion, and returns control without acting.

How do I install the Sanity Check skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add flurdy/agent-skills --skill sanity-check. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Sanity Check popular?

It lives in flurdy/agent-skills, which has 9 GitHub stars and 0 forks.

Related skills

Browse the most popular Claude skills, all other skills, or write your own with the skills generator.