nexu is an open-source desktop client that connects an OpenClaw AI agent to messaging services such as WeChat, Feishu, Slack, and Discord. It is for people who want to chat with their agent from those channels using their own model credentials while keeping data on their computer, and the catalogue entries support its agent workflows.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/nexu-io/nexu/sync-specsnpx skills add nexu-io/nexu --skill sync-specsgit clone --depth 1 https://github.com/nexu-io/nexuWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/nexu-io/nexu/sync-specs)<a href="https://agentmods.dev/skills/nexu-io/nexu/sync-specs"><img src="https://agentmods.dev/badge/skills/nexu-io/nexu/sync-specs.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00031 | $0.01261 |
| Opus 5 | $0.00015 | $0.00630 |
| Sonnet 5 | $0.00006 | $0.00252 |
| Haiku 4.5 | $0.00003 | $0.00126 |
Grade A, and why
sync-specs scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation Sync
Review code changes and update project documentation for consistency.
Mode
| Mode | How to activate | Behavior |
|---|---|---|
delta (default) |
No argument, or say "delta" | Diff against merge-base with origin/main + working tree changes |
full |
Say "full audit" or "full sync" | Complete audit of all docs against current codebase |
| Scope keyword | Say the keyword (e.g. "db", "api") | Targeted check (see Scope Filters below) |
Delta Mode Baseline
Identify changed files using merge-base (not a fixed commit count):
# Branch changes since diverging from main
git diff --name-only $(git merge-base HEAD origin/main)...HEAD
# Plus staged + unstaged
git diff --name-only --cached
git diff --name-only
Combine the results into a single list of changed files. Then use the Impact Mapping to identify which docs may need updates.
Impact Mapping
Map changed areas to the docs they affect:
| Changed area | Affected docs |
|---|---|
apps/controller/src/routes/ |
specs/references/api-patterns.md, ARCHITECTURE.md, specs/product-specs/*.md (if route is user-facing) |
apps/web/src/pages/ or apps/web/src/app.tsx |
specs/FRONTEND.md |
apps/landing/ |
ARCHITECTURE.md (Monorepo layout) |
apps/controller/src/runtime/ |
ARCHITECTURE.md, specs/RELIABILITY.md |
packages/shared/src/schemas/ |
ARCHITECTURE.md (Type safety) |
package.json scripts |
CLAUDE.md + AGENTS.md Commands sections |
| New apps/packages dirs | ARCHITECTURE.md (Monorepo layout) |
| Config generator | specs/references/openclaw-config-schema.md, specs/openclaw-config-reference.md |
| Auth changes | specs/SECURITY.md |
| New/moved doc files | CLAUDE.md Doc Map, AGENTS.md Where to look, relevant index files |
Cross-Reference Pairs
Always verify consistency between these paired docs:
CLAUDE.mdCommands section <->AGENTS.mdCommands section (same entries)CLAUDE.mdDocumentation Map paths <-> actual files on diskCLAUDE.mdHard Rules <->AGENTS.mdHard rulesARCHITECTURE.mdmonorepo layout <-> actualapps/+packages/dirsspecs/DESIGN.mdtable <-> actualspecs/design-specs/+specs/designs/contentsspecs/design-specs/index.mdtable <-> actual design filesspecs/product-specs/index.mdtable <-> actualspecs/product-specs/*.mdfilesspecs/PLANS.mdtable <->specs/exec-plans/{active,completed}/contentsspecs/FRONTEND.mdPages table <->apps/web/src/app.tsxroutes
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 99 lines · 31 tokens per session scan A db3cdaa2f1d0
sync-specs is a skill published in the GitHub repository nexu-io/nexu (3,264 stars, last pushed 4mo ago), licensed MIT. It adds 31 tokens to every session and 1,261 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
clip-hand-skill
Expert knowledge for AI video clipping — yt-dlp downloading, whisper transcription, SRT generation, and ffmpeg processing.
predictor-hand-skill
Expert knowledge for AI forecasting — superforecasting principles, signal taxonomy, confidence calibration, reasoning chains, and accuracy tracking.
researcher-hand-skill
Expert knowledge for AI deep research — methodology, source evaluation, search optimization, cross-referencing, synthesis, and citation formats.
twitter-hand-skill
Expert knowledge for AI Twitter/X management — API v2 reference, content strategy, engagement playbook, safety, and performance tracking.
collector-hand-skill
Expert knowledge for AI intelligence collection — OSINT methodology, entity extraction, knowledge graphs, change detection, and sentiment analysis.
lead-hand-skill
Expert knowledge for AI lead generation — web research, enrichment, scoring, deduplication, and report generation.