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 skills add TheophilusChinomona/claude-openclaw-plugin --skill openclaw-agent-updatergit clone --depth 1 https://github.com/TheophilusChinomona/claude-openclaw-pluginWrote 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/theophiluschinomona/claude-openclaw-plugin/openclaw-agent-updater)<a href="https://agentmods.dev/skills/theophiluschinomona/claude-openclaw-plugin/openclaw-agent-updater"><img src="https://agentmods.dev/badge/skills/theophiluschinomona/claude-openclaw-plugin/openclaw-agent-updater/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/theophiluschinomona/claude-openclaw-plugin/openclaw-agent-updater"><img src="https://agentmods.dev/badge/skills/theophiluschinomona/claude-openclaw-plugin/openclaw-agent-updater.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00223 | $0.02474 |
| Opus 5 | $0.00112 | $0.01237 |
| Sonnet 5 | $0.00045 | $0.00495 |
| Haiku 4.5 | $0.00022 | $0.00247 |
Grade A, and why
openclaw-agent-updater 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 11d 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 — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenClaw Agent Updater
Surgically update existing OpenClaw agent workspace files based on business changes, conversational requests, and evolving context — without touching the soul.
What This Skill Does
Agents go stale. A new client is signed, an invoice is paid, a service is deprecated, a goal is completed, a cron job needs adjusting. This skill handles all of it — precisely, surgically, with a preview before any change is made.
What it NEVER changes (soul-protected):
## Core Valuesin SOUL.md## Boundariesin SOUL.md## Vibein SOUL.md## Communication Stylephilosophy in SOUL.mdIDENTITY.mdentirely- Any hard limit (
NEVERrule) in AGENTS.md
What it CAN change:
## Contextsection in SOUL.md (business facts, reporting lines, tools)MEMORY.md— any section (add clients, update invoices, log lessons)GOALS.md— add goals, update status, move to completed, change prioritiesAGENTS.md— workflows, tool access, escalation rules, report formatsHEARTBEAT.md— checklist itemsUSER.md— owner preferences or contact detailsopenclaw.json— model, heartbeat interval, cron jobs, bindings, channel config
Change Classification
Before making any edit, classify the incoming request:
| Change Type | Affects | Example |
|---|---|---|
| Business event | MEMORY.md, GOALS.md | "RPS paid the invoice", "New client: Tivanathi Phase 2" |
| Goal update | GOALS.md | "Mark the IBS website goal complete", "Add P1 goal for new tender" |
| Client update | MEMORY.md (client file) | "RPS contact is now Thabo Dlamini", "Tripli scope expanded" |
| Context change | SOUL.md context section | "We now also offer R&D tax consulting", "Reporting to APEX changed" |
| Operational change | AGENTS.md | "HUNTER's follow-up cadence is now 21 days max", "Add PITCH to NEXUS's doc workflow" |
| Infrastructure change | openclaw.json, HEARTBEAT.md | "Change SENTINEL to check every 4h", "Add new cron job for EDGE" |
| Memory add | MEMORY.md | "Remember that Givemore prefers WhatsApp voice notes" |
| Lesson learned | MEMORY.md (lessons section) | "Add: always confirm RPS audit dates 2 weeks out" |
| Stale cleanup | GOALS.md, MEMORY.md | "Remove the completed ESK tender goal", "Archive Tripli invoice" |
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.
- 11d ago First seen · 244 lines · 223 tokens per session scan A 6ed1913ce63f
openclaw-agent-updater is a skill published in the GitHub repository TheophilusChinomona/claude-openclaw-plugin (2 stars, last pushed 5mo ago), licensed MIT. It adds 223 tokens to every session and 2,474 once invoked, about $0.0011 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…