conorbronsdon

83 mods across 19 repositories, 3.9k stars between them.

reconcile

27

conorbronsdon/agent-context-os

Command Claude Code

Scan multi-session drift and offer individually reviewed fixes only after explicit approval.

15 2d ago A 17 tokens original MIT

recover

28

conorbronsdon/agent-context-os

Command Claude Code

Scan orphaned worktrees and stale branches, then offer explicit approval-gated cleanup.

15 2d ago A 19 tokens original MIT

start

30

conorbronsdon/agent-context-os

Command Claude Code

Start a session — load state files, flag staleness, and give a briefing on current priorities, deadlines, and blockers.

15 2d ago A 27 tokens original MIT

today

31

conorbronsdon/agent-context-os

Command Claude Code

Create a morning heartbeat from repository state and update the local heartbeat log.

15 2d ago A 16 tokens original MIT

update

32

conorbronsdon/agent-context-os

Command Claude Code

Mid-session checkpoint — append progress to today's session log and update state files if a priority shifted, without ending the session.

15 2d ago A 25 tokens original MIT

SessionStart

33

conorbronsdon/agent-context-os

Hook Claude Code

Runs when a session starts, executing session-start.sh and branch-hygiene.sh via bash (2 commands). From conorbronsdon/agent-context-os.

15 2d ago A tokens not measured copy · 52% MIT

PreToolUse

34

conorbronsdon/agent-context-os

Hook Claude Code

Runs before the agent uses a tool for Edit and Write tool calls, executing ssot-guard.sh and worktree-guard.sh via bash (2 commands). From conorbronsdon/agent-context-os.

15 2d ago A tokens not measured copy · 44% MIT

skill-creator

36

conorbronsdon/agent-context-os

Skill Claude CodeCodex

Generate a new skill from a plain-language description — decides invocation control, arguments, and context cost, then scaffolds, validates, and tests it.

15 2d ago A 33 tokens original MIT

conorbronsdon/agent-context-os

Instructions file CodexOpenCode

Instructions for conorbronsdon/agent-context-os, covering context os, session lifecycle, lifecycle kernel, context routing and safety.

15 2d ago A 1,065 tokens original MIT

conorbronsdon/agent-context-os

Instructions file

Instructions for conorbronsdon/agent-context-os, covering who i am, slash commands (claude code), when to load additional context, thought-partner mode and safety contract.

15 2d ago A 1,153 tokens original MIT

press-outreach

39

conorbronsdon/agent-context-os

Skill Claude CodeCodex

Draft a cold pitch email to a music blog, playlist curator, or press contact. Load artist-context.md and promotion-strategy.md before running. Use when asked to "pitch [outlet]," "draft an email to [curator/blog]," or "write a press pitch.".

15 2d ago A 60 tokens original MIT

social-post

40

conorbronsdon/agent-context-os

Skill Claude CodeCodex

Write a platform-native social media post for a music release, show announcement, or general artist content. Load artist-context.md and promotion-strategy.md before running. Use when asked to "write a caption," "write a post for [platform]," or "help me announce [thing].".

15 2d ago A 61 tokens original MIT

avoid-ai-writing

41

conorbronsdon/agent-context-os

Skill Claude CodeCodex

Audit and rewrite content to remove AI writing patterns ("AI-isms"). Use this skill when asked to "remove AI-isms," "clean up AI writing," "edit writing for AI patterns," "audit writing for AI tells," or "make this sound less like AI." Pairs with writing-voice for full voice alignment.

15 2d ago A 70 tokens original MIT

angel-diligence

42

conorbronsdon/agent-skills

Skill Claude CodeCodex

Pre-investment research and deal-memo generation for angel investors. Use when asked to "diligence [company]", "research this startup for an investment", "build a deal memo", or to prep for a founder call. Runs parallel web research with strict citation rules and produces a nine-section memo that separates verified…

9 25d ago A 79 tokens original MIT

code-review

43

conorbronsdon/agent-skills

Skill Claude CodeCodex

Multi-agent deep review for code PRs in any repo. Use when asked to "deep review this PR," "multi-agent review," "review.

9 25d ago A 32 tokens original MIT

eval-integrity

44

conorbronsdon/agent-skills

Skill Claude CodeCodex

Audit an LLM evaluation or benchmark repo for integrity and credibility practices. Use when asked to "audit my benchmark," "is my eval trustworthy," "check my leaderboard for contamination," "review this benchmark's methodology," or "what would a reviewer attack in my eval." Greps the target repo for evidence across…

9 25d ago A 107 tokens original MIT

guest-circuit

45

conorbronsdon/agent-skills

Skill Claude CodeCodex

Podcast-appearance research for guest booking. Use when asked to "map someone's podcast circuit," "where has X podcasted," "research X before guest outreach," or "find an unclaimed angle for X." Sweeps Podcast Index, web search, and the guest's own channels in parallel, then delivers a circuit report: appearance…

9 25d ago A 89 tokens original MIT

reconcile

46

conorbronsdon/agent-skills

Skill Claude CodeCodex

Tripwire check for multi-session drift. Scans state files, recent commits, and file conflicts caused by parallel Claude Code sessions.

9 25d ago A 29 tokens original MIT

recover

47

conorbronsdon/agent-skills

Skill Claude CodeCodex

Scan for orphaned worktrees and stale branches after crashes or abandoned sessions. Offers safe cleanup options.

9 25d ago A 22 tokens original MIT

session-management

48

conorbronsdon/agent-skills

Skill Claude CodeCodex

Structured session lifecycle for Claude Code — start, checkpoint, end, and daily heartbeat commands that maintain project state across conversations.

9 25d ago A 27 tokens original MIT