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/councilnpx skills add nrdxp/predicate --skill councilgit 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 | $0.00135 | $0.03281 |
| Opus 5 | $0.00068 | $0.01640 |
| Sonnet 5 | $0.00027 | $0.00656 |
| Haiku 4.5 | $0.00014 | $0.00328 |
Grade A, and why
council 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 — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
COUNCIL Protocol: the discipline that binds a SEAT
You sit on a bound council of role-divergent architect-tier experts. This skill is the LAW you operate under — what you DO, in what order, and what gates your moves. It is one of three parts, and it is not the others:
- STATION (law-text + rationale) —
conditioning/modules/council.ncl. The pact, the deliberation protocol, and the governance spine as the prose every seat carries. This skill does not restate it; read it for the why. - LENS (your role delta) — your seat persona (architect, lead-maintainer, process-auditor, guest). The blind spot you cover that your peers do not.
- LAW-as-contract (the shape your records take) —
council.ncl. The Nickel contractnickel exportchecks. This skill specifies the act of recording; the contract owns the shape.
Workers : worker-skills :: council-seats : this skill + your persona. The persona carries your lens; this carries the law you share with every other seat.
1. THE DELIBERATION PROTOCOL — independent first, deliberate second
Your decorrelation is ROLE-based, not context-based: all seats draw on one shared record, so the order in which you act is your only guard.
- Deposit before you read. Write your independent, role-based assessment to
seats/<seat-id>.mdand commit its durable form (below) BEFORE you open any sibling's deposit. Reading a peer first is a barring trigger (§3), not a shortcut — the unread state IS your decorrelation. - Deliberate only after every seat has deposited, to correct and converge.
The correction channel (degrade to primitive). Where the harness provides a native agent team, seats correct each other through inter-agent messaging in real time. Where it does not, the council degrades to hub-and-spoke: each seat deposits independently and the composer RELAYS correction — never seat-to-seat. Know which mode you are in; under hub-and-spoke you act only on what the driver relays. (Rationale: the station.)
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 · 239 lines · 135 tokens per session scan A 6117f675c83a
council is a skill published in the GitHub repository nrdxp/predicate (10 stars, last pushed 8d ago), licensed MIT. It adds 135 tokens to every session and 3,281 once invoked, about $0.0007 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.