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/nevaberry/nevaberry-plugins/chrony-knowledge-patchnpx skills add Nevaberry/nevaberry-plugins --skill chrony-knowledge-patchgit clone --depth 1 https://github.com/Nevaberry/nevaberry-pluginsWhat 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 | $0.00009 | $0.02576 |
| Opus 5 | $0.00005 | $0.01288 |
| Sonnet 5 | $0.00002 | $0.00515 |
| Haiku 4.5 | $0.00001 | $0.00258 |
Grade A, and why
chrony-knowledge-patch 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 3d 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 — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
chrony 4.7–4.8 Knowledge Patch
Reference index
| Reference | Topics |
|---|---|
| core-configuration.md | Upgrade requirements, daemon and client behavior, source options, packet controls, logging, service integration |
| reference-clocks.md | RTC, PHC, PPS, GPS, gpsd, reachability, locking, startup, and time scales |
| hardware-timestamping-and-ptp.md | Hardware timestamping, interleaved NTP, NTP-over-PTP, transparent clocks, PHCs, and virtualization |
| network-time-security.md | NTS client state, authentication diagnostics, server setup, policy compatibility, and verification |
| monitoring-and-troubleshooting.md | chronyc, exporter metrics, source selection, transport errors, client records, and network recovery |
Using this patch
- Check the upgrade notes before carrying an older configuration or build setup forward.
- Use the quick references below for common decisions, then load the indexed topic file for constraints and edge cases.
- Treat examples as fragments: retain the access controls, source diversity, measured offsets, and platform-specific paths required by the deployment.
Breaking changes and upgrade checks
Configuration and build compatibility
- Since 4.7, integer configuration values receive sanity checks. Values that were accepted despite being nonsensical can now fail validation.
- NTS builds require Nettle 3.6 or newer and GnuTLS 3.6.14 or newer.
- Building without POSIX threads is no longer supported.
- On RHEL, the FIPS and OSPP profiles are incompatible with NTS and can make an NTS-configured daemon exit fatally. A service-only exception can be set in
/etc/sysconfig/chronyd:
GNUTLS_FORCE_FIPS_MODE=0
Security and compatibility behavior
- In 4.8, root-run
chronyc -udrops privileges to the configured client user. - The
chronycsocket is hidden to prevent unsafe permission changes against it. - Keep both endpoints of an NTP-over-PTP connection on the same chrony version.
- Do not discipline the physical PHC used for hardware-timestamped NTP-over-PTP; use a virtual clock if PTP must share the interface.
What ships with it
6 files 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.
- 3d ago First seen · 211 lines · 9 tokens per session scan A bd557c412d6b
chrony-knowledge-patch is a skill published in the GitHub repository Nevaberry/nevaberry-plugins (24 stars, last pushed 7d ago), licensed MIT. It adds 9 tokens to every session and 2,576 once invoked, about $0.0000 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
api-workers
Cloudflare Workers deployment using createWorkerHandler from @cyanheads/mcp-ts-core/worker. Covers the full handler signature, binding types, CloudflareBindings extensibility, runtime compatibility guards, and wrangler.toml requirements.
healthcheck
Host security hardening and risk-tolerance configuration for OpenClaw deployments. Use when a user asks for security audits, firewall/SSH/update hardening, risk posture, exposure review, OpenClaw cron scheduling for periodic checks, or version status checks on a machine running OpenClaw (laptop, workstation, Pi, VPS).
design-mcp-server
Design the tool surface, resources, and service layer for a new MCP server. Use when starting a new server, planning a major feature expansion, or when the user describes a domain/API they want to expose via MCP. Produces a design doc at docs/design.md that drives implementation.
api-canvas
DataCanvas primitive reference — a Tier 3 SQL/analytical workspace for tabular MCP servers, backed by DuckDB. Use when registering tables from upstream APIs, running ad-hoc SQL across them, and exporting results. Covers the acquire → register → query → export flow, per-table TTL, the token-sharing pattern for…
api-errors
McpError constructor, JsonRpcErrorCode reference, and error handling patterns for @cyanheads/mcp-ts-core. Use when looking up error codes, understanding where errors should be thrown vs. caught, or using ErrorHandler.tryCatch in services.
field-test
Exercise tools, resources, and prompts against a live HTTP server via MCP JSON-RPC over curl. Starts the server, surfaces the catalog, runs real and adversarial inputs, and produces a tight report with concrete findings and numbered follow-up options. Use after adding or modifying definitions, or when the user asks to…