Borrowing it
Nothing to install: this file belongs to dkushnikov/nestor-plugin. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/dkushnikov/nestor-plugin/main/CLAUDE.mdgit 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/instructions/dkushnikov/nestor-plugin/claude-md)<a href="https://agentmods.dev/instructions/dkushnikov/nestor-plugin/claude-md"><img src="https://agentmods.dev/badge/instructions/dkushnikov/nestor-plugin/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/dkushnikov/nestor-plugin/claude-md"><img src="https://agentmods.dev/badge/instructions/dkushnikov/nestor-plugin/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00437 | $0.00437 |
| Opus 5.5 | $0.00175 | $0.00175 |
| Sonnet 5.5 | $0.00087 | $0.00087 |
| Haiku 4.5 | $0.00044 | $0.00044 |
Grade A, and why
nestor-plugin CLAUDE.md 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 6d 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
nestor — Claude Code plugin
Council of frontier models for high-stakes decisions. The plugin is one skill plus references — no agent, no MCP server, no storage. The calling session executes the protocol; pal MCP (external, user-scope) talks to the models.
Quick reference
- Type: plugin (skill only)
- Core:
plugins/nestor/skills/nestor/SKILL.md→references/(presets, consensus execution, stage 2, stances, router cases, setup) - Requires:
mcp__pal__consensus+mcp__pal__chat(seereferences/setup.md)
Development
claude plugin validate .
python3 -m pytest -q -rs tests/ # doc checks + private-token scan + consensus state contract (needs PAL_SRC; without it 5 tests SKIP — -rs shows why)
git config core.hooksPath .githooks # pre-push: token scan over tree and outgoing messages
# A marketplace added from a local path loads the source in place: an edit is live at the next
# session start or /reload-plugins — nothing to redeploy. GitHub installs load a cached copy keyed by
# the "version" in plugins/nestor/.claude-plugin/plugin.json: a change ships only after BOTH a bump AND
# a push to main (same string = «already at the latest version»). Refresh a cached install after the push:
claude plugin marketplace update nestor-plugin
claude plugin update nestor@nestor-plugin # per scope: -s user / -s local; restart the session
Roster changes go through design review and a dated entry in references/presets.md §Refresh history, never a runtime edit — and every new id gets an entry in references/openrouter-models.example.json (tests/test_doc_links.py fails otherwise). This repository is public: no personal names, home paths or private project references in files or commit messages (the test enforces it).
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.
- 6d ago Changed · +3 lines · +134 tokens per session 3ae2ebb04ef8
- 7d ago First seen · 24 lines · 303 tokens per session scan A 42c47418123f
nestor-plugin CLAUDE.md is an instructions file published in the GitHub repository dkushnikov/nestor-plugin (2 stars, last pushed 6d ago), licensed MIT. It adds 437 tokens to every session, about $0.0017 per session on Opus 5.5. 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 2026-10-28.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.