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/nrdxp/predicate/orchestrationnpx skills add nrdxp/predicate --skill orchestrationgit clone --depth 1 https://github.com/nrdxp/predicateWhat 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 | $0.00130 | $0.09685 |
| Opus 5 | $0.00065 | $0.04842 |
| Sonnet 5 | $0.00026 | $0.01937 |
| Haiku 4.5 | $0.00013 | $0.00968 |
Grade A, and why
orchestration 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.
How it starts
The opening of the file, as written. The whole thing — 544 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orchestration: Driving the Campaign Execution Protocol
/orchestrate is the runnable layer that executes
docs/orchestration-protocol.md over a
live validated DAG. The protocol document is the spec — the exact procedure,
the exit-code routing, the four [HUMAN SEAM]s. This skill does not restate that
procedure; it lifts it to a state machine a runner walks and wires its abstract
steps to concrete repo commands. Where the spec says "assert the structural gate
exits 0," this skill says which command, with which arguments, and what each exit
code branches to.
It slots between campaign's §DISPATCH and §RECONCILE — the two steps campaign already delegates by reference to the protocol. Until this skill is invoked, the composer drives the protocol by hand; invoked, it drives DISPATCH ⇄ RECONCILE as a loop a cheap-tier runner can replay.
[!IMPORTANT] Non-duplication pointer. This skill does not re-specify campaign mechanics. campaign/SKILL.md §6 DISPATCH and §7 RECONCILE own the narrative (what the council decides, the tier routing, the worker IBC contract); docs/orchestration-protocol.md owns the deterministic procedure (the pseudocode + exit-code rules). This skill is strictly the driver: it names protocol steps and sequences their commands. If you find yourself explaining why a step exists or how the council judges, you have left orchestration space — that prose lives in campaign and the protocol, link to it.
Inputs (the driver's contract)
The protocol declares the inputs an orchestrator needs
(protocol §"inputs", lines 19-24). This
skill makes them an explicit, parameterized contract — the protocol's
pseudocode and ledger/derive/layers.ncl reference the project-state DAG by a
fixed path; a driver run binds that path, it does not hardcode it.
What ships with it
4 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 · 544 lines · 130 tokens per session scan A c50a8f3e8269
orchestration is a skill published in the GitHub repository nrdxp/predicate (10 stars, last pushed 8d ago), licensed MIT. It adds 130 tokens to every session and 9,685 once invoked, about $0.0006 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
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…