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/dkushnikov/nestor-plugin/nestornpx skills add dkushnikov/nestor-plugin --skill nestorgit clone --depth 1 https://github.com/dkushnikov/nestor-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/dkushnikov/nestor-plugin/nestor)<a href="https://agentmods.dev/skills/dkushnikov/nestor-plugin/nestor"><img src="https://agentmods.dev/badge/skills/dkushnikov/nestor-plugin/nestor.svg" alt="Measured on agentmods" 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 | $0.00186 | $0.05734 |
| Opus 5 | $0.00093 | $0.02867 |
| Sonnet 5 | $0.00037 | $0.01147 |
| Haiku 4.5 | $0.00019 | $0.00573 |
Grade A, and why
nestor 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 5d 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 — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nestor
Nestor is a named consultation mode for multi-model deliberation. When the user or the session needs a multi-model council on a hard decision, invoke this skill to run the deliberation through a disciplined protocol: self-contained question formulation, routing, council execution, synthesis, and structured presentation back to the user.
This skill is self-contained. The core protocol — triggers, router, envelopes, presentation, kill criteria — lives in this file. Detailed deliberation mechanics (preset model rosters, fallback chains, the pal.consensus step-by-step workflow, stance semantics with the Gemini Flip empirical finding, and the deliberative stage-2 cross-critique template) live in references/ within this skill and are loaded on demand:
references/presets.md— model rosters forarch/code/research/brainstorm/quickplus per-vendor fallback chainsreferences/consensus-execution.md—mcp__pal__consensusstep-by-step workflow,continuation_idhandling, stepping disciplinereferences/stances-and-gemini-flip.md— stance semantics (for/against/neutralas roleplay-not-belief) and the Gemini Flip findingreferences/deliberative-stage-2.md— cross-critique protocol, the verbatim critique prompt template, anti-patterns
When to invoke
Invoke this skill when:
The user uses an explicit trigger phrase (already matched by the skill loader via the description above). The full phrase list: "ask Nestor", "go to Nestor", "сходи к Нестору", "третье мнение", "что думает совет", "прогони через совет", "глубокий разбор" (→ forces deliberative mode), "важное решение", "критично", "high stakes", "critical decision", "think carefully", "deliberate", "council", "совет", "спросить модели", "second opinion", "что думают другие", "what does the council think".
An implicit condition matches and you decide to delegate without being asked:
- Architectural or strategic decisions with high irreversibility
- The session's current answer feels under-calibrated or session-biased
- A hypothesis built with the user across the session needs pressure-testing from outside the session's framing
- An open question where the shape of disagreement is unknown
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.
- 5d ago First seen · 237 lines · 186 tokens per session scan A c4b6eac198f6
nestor is a skill published in the GitHub repository dkushnikov/nestor-plugin (2 stars, last pushed 14d ago), licensed MIT. It adds 186 tokens to every session and 5,734 once invoked, about $0.0009 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…
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…