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/nxtsoft/cgraph/always-onnpx skills add Nxtsoft/CGraph --skill always-ongit clone --depth 1 https://github.com/Nxtsoft/CGraphWhat 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 | $0.00000 | $0.00307 |
| Opus 5 | $0.00000 | $0.00153 |
| Sonnet 5 | $0.00000 | $0.00061 |
| Haiku 4.5 | $0.00000 | $0.00031 |
Grade A, and why
always-on 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 2d 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.
What it actually says
Always-On Graph Integration
Use this skill when an always-on host wants graph context or semantic enrichment while keeping provider choice and token spend under host control.
Contract
Follow the Host Skill Contract in docs/host-skill-contract.md.
The native binary provides deterministic graph commands, chunk planning, fragment validation, semantic cache records, and local graph mutation. The host owns model selection and dispatch. This integration has no provider logic and does not require provider credentials.
Command Routing
Use cgraph-client for all graph operations:
statusto observe deterministic readiness andenrichment_statequeryfor graph searchpathfor graph pathsexplainfor node neighborhoodsupdate .for full stat-index rescanshutdownfor clean daemon exit
Set CGRAPH_PROJECT_ROOT to the project root. Set CGRAPH_DAEMON only when the host must use a specific daemon binary.
Semantic Work
When status or host policy indicates stale semantic inputs, request or compute chunk work according to the contract. Host workers write completed fragments as chunk_NN.json files into the semantic drop directory.
The daemon validates every fragment before mutation. Malformed fragments are rejected and leave the graph unchanged. Valid fragments update the semantic cache by content hash.
Runner
Use integrations/always-on/cgraph-always-on.sh as the reference loop for host processes that need periodic graph status checks and optional deterministic refreshes.
What ships with it
2 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.
- 2d ago First seen · 33 lines · 0 tokens per session scan A 898b8946533a
always-on is a skill published in the GitHub repository Nxtsoft/CGraph (2 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 307 tokens. 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
mcporter
List, auth, and call MCP servers/tools from the terminal.
agent-messaging
Send and receive cryptographically signed messages between AI agents using the Agent Messaging Protocol (AMP). Use when the user asks to "send a message to an agent", "check agent inbox", "message another agent", "reply to a message", "notify an agent", or any inter-agent communication task.
📝 任务完成后归档
重要提醒: 每次完成复杂调试或开发任务后，主动执行此流程！ 将学到的经验归档为 skill，供以后参考。不要等用户提醒。.
oracle
Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).
agent-mode
Unified tool for managing agent LLM modes (add, remove, update, list, switch).
agento11y-prod-setup
Sets up production evaluation and guardrails for a DEPLOYED AI agent in Grafana Agent Observability, grounded in the agent's own code and its real ingested traffic. The judgment layer on top of the agento11y skill: it reads the agent's source (system prompt, tools, entrypoint) AND samples its live traffic via gcx…