复制安装命令
用 Codex 或 Claude 安装复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它先审查 Skill 页面再帮你安装。
复制前请先查看来源、License 和安全提示。
Essays and writing behind this toolkit live at vexjoy.com.
用 Codex 或 Claude 安装复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它先审查 Skill 页面再帮你安装。
复制前请先查看来源、License 和安全提示。
来源文件:README.md
Essays and writing behind this toolkit live at vexjoy.com.
AI agents skip steps.
"Looks correct" replaces running tests. "Trivial change" replaces verification. The agent confidently ships broken code because nothing structurally prevented it from skipping the work.
Harnesses have a second problem: given only a skill list, they do not route eagerly enough, or correctly enough. Good skills sit unused. So this toolkit connects the skills, agents, and workflows we want directly into the harness, automatically. You don't have to understand what is here. Say what you want in plain English and you get all the value we have put into it: the right specialist with the right methodology, behind gates that demand exit codes, not assertions.
44 domain agents, 122 workflow skills, 78 hooks, 136 scripts. Agents carry knowledge, skills enforce methodology, hooks block incomplete work, scripts handle determinism.
Works across Claude Code (/do), Codex ($do), Factory (/do), Reasonix (/do).
$ claude
> /do debug this Go test
Routing: go-engineer + systematic-debugging
Phase 1/4: Reproduce: running test, capturing failure...
Phase 2/4: Hypothesize: 3 candidates from stack trace...
Phase 3/4: Verify: isolated root cause in connection pool timeout
Phase 4/4: Fix: patch applied, test passing, PR opened
✓ Delivered: PR #847, fix connection pool timeout in health check
The router reads intent, picks a Go agent paired with a debugging skill, and runs the full lifecycle. You typed one sentence. The system did the rest.
ROUTE PLAN EXECUTE VERIFY DELIVER RECORD
┌──────┐ ┌──────┐ ┌──────┐ ┌──────┐ ┌──────┐ ┌──────┐
│ /do │───▶│ Task │───▶│Agent │───▶│Tests │───▶│ PR │───▶│Route │
│Router│ │ Plan │ │+Skill│ │Gates │ │Branch│ │Result│
└──────┘ └──────┘ └──────┘ └──────┘ └──────┘ └──────┘
This is the single thing that separates it from "agent with a system prompt."
| Agent Says | What Happens |
|---|---|
| "Code looks correct, skip tests" | Exit gate requires test output. Blocked. |
| "Trivial change, no verification" | Hook blocks completion without evidence. |
| "Similar to before" | Skill demands case-specific proof. |
| "User is in a hurry" | Protocol overrides time pressure. |
| "I'm confident" | Gate demands exit code, not assertion. |
Hooks fire automatically. Gates block completion. Skills encode counter-arguments at every skip-worthy step. The agent verifies or it doesn't finish.
For what I do, the difference is enormous. If you're doing simple single-file edits, maybe less so.
The same routing serves knowledge work. The content engine researches, drafts in a calibrated voice, validates against 397 AI patterns, and repurposes finished pieces for each platform. /html turns any request into a single self-contained HTML file: report, slide deck, prototype, data viz, diagram. Non-engineers who try the toolkit consistently name the HTML artifacts as the thing they love. No code, no setup beyond the installer.
Changes to the toolkit itself ship with evidence. New skills get blind A/B tests against a no-skill baseline before merge. Routing and writing-standard decisions carry measured verdicts; PHILOSOPHY.md cites the numbers. Experiments that lost go into the negative-results registry, what-didnt-work.md; the registry now covers routing reversals, unvalidated A/B citations, and disabled lint rules alongside the original program refutations.
The automated nightly evolution loop (/evolve, writes to evolution-reports/) ran regularly through mid-May 2026. It is currently dormant; recent evidence has come from manual PRs instead.
git clone https://github.com/notque/vexjoy-agent.git ~/vexjoy-agent
cd ~/vexjoy-agent
./install.sh
Links into ~/.claude/ and mirrors into ~/.codex/, ~/.factory/, ~/.reasonix/ — each mirror only when that runtime is detected (its command on PATH or its home dir already exists). The installer asks symlink (live updates via git pull) or copy (stable snapshot).
Want only part of the toolkit? Run ./install.sh --configure to pick which skills, agents, and hooks install, or copy .local.example/profile.yaml to .local/profile.yaml and edit. No profile file = full install, unchanged behavior. Credit: @thomasvan. Details: .local.example/README.md.
| CLI | Entry Point |
|---|---|
| Claude Code | /do |
| Codex | $do |
| Factory | /do |
| Reasonix | /do |
Full setup: docs/start-here.md
Mirrors agents, skills, and supported hooks into ~/.codex/. The original six-hook allowlist was correct for Codex v0.114, when tool hooks only intercepted Bash. Current support requires Codex v0.144.1+ and classifies the 74 Claude hook registrations as 26 native, 35 adapter-backed, and 13 unsupported (61 supported). These are registration counts, not unique hook files. The installer also preserves explicit per-subagent model routing for GPT-5.6 Sol by setting the MultiAgent V2 compatibility keys documented in openai/codex#31814.
Codex now exposes apply_patch to tool hooks. VexJoy's adapter converts each patch operation into the Write/Edit payload expected by existing guards, but it cannot intercept writes performed through unified_exec, unmatched MCP tools, WebSearch, or other unsupported tool paths. PreCompact and Stop adapters also receive less telemetry than Claude Code: Codex does not provide Claude's conversation_history or session_data. This is expanded compatibility, not full Claude parity.
After install or any hook-definition change, run /hooks in Codex and review the new definitions before trusting them. Codex hash-trusts hook commands and skips changed, unreviewed definitions.
Gemini CLI support removed (deprecated upstream, transitioned to Antigravity CLI); Antigravity support pending CLI maturity. Per Google's transition announcement, Gemini CLI stops serving requests on 2026-06-18 for Google AI Pro / Ultra and free Gemini Code Assist for individuals. Gemini API integrations (image-gen backends, sprite pipeline, GEMINI_API_KEY) are unaffected and stay in the toolkit.
If a prior install mirrored into ~/.gemini/, remove the stale mirrors with:
rm -rf ~/.gemini/skills ~/.gemini/agents ~/.gemini/hooks ~/.gemini/scripts ~/.gemini/antigravity/plugins/vexjoy-agent
Mirrors agents (as "droids"), skills, and all hooks into ~/.factory/. Hook config merges into ~/.factory/settings.json with paths rewritten.
Mirrors skills, scripts, and the allowlisted hooks (scripts/reasonix-hooks-allowlist.txt) into ~/.reasonix/ (no agent or custom-command surface, so neither is installed; the /do router rides in as a skill). Reasonix fires only 4 events (PreToolUse, PostToolUse, UserPromptSubmit, Stop), so only hooks for those events are allowlisted. Hook config is written to the hooks key of ~/.reasonix/settings.json in Reasonix's native flat shape (one entry per hook, match regex over the tool name); the generator builds absolute python3 commands, so no path rewrite is applied. MCP/model/permissions in ~/.reasonix/config.json are user-owned and left untouched.
The toolkit supplies its own routing, domain knowledge, methodology, and enforcement. The default system prompt duplicates most of that.
claude --system-prompt "."
Strips built-in tool-use instructions. The toolkit's agents, skills, hooks, and CLAUDE.md provide equivalent coverage.
| Layer | Count | Does |
|---|---|---|
| Agents | 44 | Domain knowledge: idiom tables, failure mode catalogs, error-to-fix mappings |
| Skills | 122 | Phased methodology with gates. Can't skip steps. Each phase has exit criteria requiring evidence. |
| Hooks | 78 | Fire on lifecycle events. Block incomplete work. Zero LLM cost. |
| Scripts | 136 | Determinism: test runners, linters, validators. No LLM judgment. |
Full skill catalog: docs/skills.md.
┌─────────────────────────────────────────────────┐
│ SKILL.md │
│ ┌─ Frontmatter ─────────────────────────────┐ │
│ │ triggers, pairs_with, success-criteria │ │
│ └────────────────────────────────────────────┘ │
│ Reference Loading Table (conditional imports) │
│ Phased Instructions (numbered, with gates) │
│ Verification (evidence requirements) │
└─────────────────────────────────────────────────┘
A game built entirely by Claude Code using these agents, skills, and pipelines:
I just want to use it Install, learn /do, done.
I do knowledge work Writing, research, data analysis, moderation, HTML artifacts. No code.
I'm a developer Architecture, extension points, adding agents and skills.
I'm an AI power user Routing tables, pipelines, hooks, telemetry DB.
I'm an AI agent Machine-dense inventory. Tables, paths, schemas.
I'm on LinkedIn 🚀 Thought leadership. Agree? 👇
Full design philosophy: PHILOSOPHY.md
One report-only script surfaces upkeep work; it prints a digest and never edits, deletes, or blocks.
python3 scripts/stale-skill-scan.py --top 20 ranks stale skills and agents as pruning candidates. Run it quarterly; see docs/deprecation-template.md.Scheduled work follows the same boundary as everything else: judgment uses agents; repeatable plumbing uses scripts.
| Need | Use |
|---|---|
| Run a deterministic command on a schedule | scripts/agent-scheduler.py with runner: "command" |
| Run an agent judgment on a schedule, webhook, or file change | scripts/agent-scheduler.py with the default runner: "claude" |
| Install or remove a user crontab entry safely | scripts/crontab-manager.py |
| Audit shell cron reliability | cron-automation |
| Keep one interactive objective moving until criteria verify | objective-loop |
See CONTRIBUTING.md.
MIT. See LICENSE.
name: x-api
description: "Post tweets, build threads, upload media via the X API."
user-invocable: false
agent: python-general-engineer
allowed-tools:
- Read
- Write
- Bash
- Glob
routing:
triggers:
- post to X
- post tweet
- tweet this
- build thread
- post thread
- twitter thread
- x api
- upload media to X
- read timeline
- search X
- search twitter
- publish to X
- publish to twitter
pairs_with:
- content-calendar
complexity: Medium
category: content-publishingThis skill orchestrates OAuth-authenticated, rate-limit-aware X/Twitter API interactions through a deterministic Python script (scripts/x-api-poster.py). The workflow implements a 4-phase pipeline with an explicit confirmation gate (Phase 2) to prevent accidental public posts.
Core principles:
--confirmed)Goal: Confirm credentials, content, and dependencies before any network call.
Step 1: Check credentials
Test credential presence by running a dry-run credential check:
python3 $HOME/.claude/scripts/x-api-poster.py post --dry-run --text "ping"
This confirms all required environment variables are set: X_API_KEY, X_API_SECRET, X_ACCESS_TOKEN, X_ACCESS_SECRET, X_BEARER_TOKEN.
X_BEARER_TOKEN is requiredStep 2: Validate content length
The script enforces a 280-character limit per tweet. Before posting, validate your content length:
For a single tweet:
python3 $HOME/.claude/scripts/x-api-poster.py post --dry-run --text "your tweet text here"
For a thread:
python3 $HOME/.claude/scripts/x-api-poster.py thread --dry-run --texts "part 1" "part 2" "part 3"
If --dry-run reports a length error, ask the user to shorten the text or approve auto-segmentation into a thread.
Gate: Dry run exits 0, content length validates, credentials confirmed present. Proceed only when gate passes.
Goal: Show the user exactly what will be posted and require explicit approval before writing.
This gate is mandatory because X posts are public and irreversible. Present a content preview in this format:
CONTENT PREVIEW
================
Tweet 1/1:
"Your tweet text here"
Characters: 42/280
Action: POST single tweet
Approve? [yes/no]
For a thread:
CONTENT PREVIEW
================
Tweet 1/3:
"First part text"
Tweet 2/3:
"Second part text"
Tweet 3/3:
"Third part text"
Action: POST thread (3 tweets, chained replies)
Approve? [yes/no]
Wait for explicit user approval. The words "yes", "approve", "go ahead", "post it", or equivalent typed in the current conversation turn constitute approval. Do not infer approval from context or prior conversation turns. Do not pass --confirmed before the user provides explicit typed approval.
Gate: User has typed an explicit approval in this conversation turn. Proceed only when gate passes.
Goal: Execute the write operation and capture tweet IDs.
Only proceed once Phase 2 approval is confirmed. Pass the --confirmed flag when the user approves in this turn.
Single tweet:
python3 $HOME/.claude/scripts/x-api-poster.py post \
--confirmed \
--text "your tweet text here"
Thread:
python3 $HOME/.claude/scripts/x-api-poster.py thread \
--confirmed \
--texts "part 1" "part 2" "part 3"
Tweet with media:
python3 $HOME/.claude/scripts/x-api-poster.py post \
--confirmed \
--text "your tweet text here" \
--media /absolute/path/to/image.jpg
Media constraints: Images must be <= 5 MB (JPG, PNG, GIF); videos must be <= 512 MB (MP4). Media upload is a two-step process; if either step fails, no orphaned media is left behind. Confirm the file exists and is in a supported format before posting.
Watch output for:
[tweet-posted] id=... url=... — success line per tweet; contains canonical URL (https://x.com/i/web/status/{id})[rate-limit-warning] remaining=N reset=EPOCH — surface to user immediately if presentERROR: line — surface verbatim and stopOAuth mode is automatic: Read operations use Bearer token only; write operations require full OAuth 1.0a. The script selects the mode based on operation type — do not override it.
Gate: Script exits 0, at least one [tweet-posted] line in output. Proceed only when gate passes.
Goal: Return tweet URLs, IDs, and engagement baseline to the user.
Step 1: Collect tweet IDs from Phase 3 output
Parse all [tweet-posted] id=... url=... lines from the script output.
Step 2: Read engagement baseline (optional)
For each posted tweet, you may optionally read initial engagement metrics via:
python3 $HOME/.claude/scripts/x-api-poster.py read-timeline --user-id me --max-results 5
Engagement metrics have propagation delay: X API metrics take time to populate. Reading public_metrics immediately after posting with 0 impressions is expected behavior, not failure. Report metrics as baseline at post time and note they will grow asynchronously.
Step 3: Report to user
Provide:
Cause: One or more credential env vars not set in the shell Solution:
Cause: A single tweet segment is too long Solution:
Cause: Script invoked without confirmation (should not happen if Phase 2 gate was followed) Solution: Return to Phase 2, present the confirm gate, and obtain explicit user approval
Cause: Credentials are invalid, expired, or lack the required permissions Solution:
Cause: API rate limit window exhausted Solution:
Cause: Media upload is a two-step process; failure at either step leaves no orphaned media Solution:
$HOME/.claude/scripts/x-api-poster.py: Backing script (exit codes: 0=success, 1=missing credentials, 2=content validation failed, 3=API error, 4=write attempted without --confirmed)
评论 (0)
暂无评论,成为第一个评论者吧!