Menu
/brief - Write session brief, commit, and push. Run at end of session to checkpoint all work.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | brief |
| version | 2.2.0 |
| description | /brief - Write session brief, commit, and push. Run at end of session to checkpoint all work. |
Run this at the end of a session to capture context and checkpoint all work to GitHub.
Read brief/session-brief.md to understand what was there from last session.
Overwrite brief/session-brief.md with a comprehensive brief covering:
date "+%A %Y-%m-%d %H:%M %Z" to get the real date, day of week, and local timezone rather than guessing (LLMs are unreliable at computing the day of the week, especially for future dates)This is NOT about brevity — be as thorough as needed to retain all important context.
After writing the brief, run the reflect skill to scan the conversation for learnings. This is a delegation, not a repeat of the reflect instructions. Load and follow the reflect skill.
If the project has an .agents/ directory, run the sync-skills skill with project scope (no prompt) so .agents/skills/ mirrors .claude/skills/ before committing. Only mention it if something was added or removed. If there is no .agents/ directory, skip silently — never create one.
After writing the brief, always ask the user which option they want:
Present these as a quick choice. Do NOT assume commit+push.
git status to see all changes (staged + unstaged + untracked)git log --oneline -3 to match commit message stylegit add — use specific paths, not -A)Session [N]: [1-2 sentence summary of session work]git pushCommit rules:
.env, credentials, tokens)/briefWhen asked to "read the brief" (typically at session start via /start), just read the file without modifying it. Do not commit or push in read-only mode.
Get an outside-Anthropic second opinion on any piece of work by sending it to Google Gemini with an adversarial critique prompt. Use when the user wants to pressure-test a decision, plan, assumption, blog draft, landing page, positioning statement, campaign, or chunk of code with a non-Claude model. Trigger when the user says 'devil's advocate,' 'play devil's advocate,' 'poke holes,' 'stress test this,' 'second opinion,' 'outside perspective,' 'non-Anthropic read,' 'sanity check from another model,' 'challenge this,' 'critique this from outside,' or '/devils-advocate.' This is explicitly a cross-model sanity check — do NOT substitute your own critique; the whole point is to surface blind spots Claude might share.
Analyze the current conversation for corrections, approvals, and patterns, then propose updates to the skill files that were used. Trigger with /reflect or automatically at end of /brief. Use when the user says 'reflect,' 'learn from this,' 'update the skill,' or 'remember this for next time.'
Audit all available Claude skills across user and project scopes — inventory them, map routing and overlap, score each on efficiency, reliability, clarity, maintainability, learning, currency, and safety, then produce a prioritized report and draft patches. Use when the user asks to audit, review, improve, optimize, modernize, clean up, consolidate, benchmark, or evaluate skills; to find outdated, duplicate, or inefficient skills; to identify missing skills; or to check whether skills follow current best practices. Diagnosis only — never edits a skill without explicit approval.
Start a new session. Trigger with /start at the beginning of a conversation. Reads the session brief, checks git status, summarizes where things stand, and increments the session number.
Sync Claude Code skills to Codex. Handles project-level (.claude/skills → .agents/skills) and user-level (~/.claude/skills → ~/.codex/skills). Trigger with /sync-skills or when the user mentions 'sync skills,' 'codex skills,' or 'sync to codex.'