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 instructions/nervsystems/cotlib/claude-mdgit clone --depth 1 https://github.com/NERVsystems/cotlibWhat 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 | $0.00902 | $0.00902 |
| Opus 5 | $0.00451 | $0.00451 |
| Sonnet 5 | $0.00180 | $0.00180 |
| Haiku 4.5 | $0.00090 | $0.00090 |
Grade A, and why
cotlib 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 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
cotlib is a Go library for creating, validating, and working with Cursor-on-Target (CoT) events. CoT is an XML-based protocol used for situational awareness, originally developed by MITRE and extended by TAK (Team Awareness Kit) applications.
Build and Test Commands
# Build the library (requires CGO for libxml2-based schema validation)
go build ./...
# Build without schema validation (no CGO required)
go build -tags novalidator ./...
# Run all tests
go test -v ./...
# Run tests for a specific package
go test -v ./cottypes
go test -v ./validator
# Run a single test
go test -v -run TestEventCreation ./...
# Run benchmarks
go test -bench=. ./...
# Regenerate type catalog (after modifying XML type definitions)
go generate ./cottypes
# Format code before committing
gofmt -s -w $(git ls-files '*.go')
# Run security scanner
go install github.com/securego/gosec/v2/cmd/gosec@latest && gosec -no-fail ./...
Architecture
Core Package (cotlib)
The main package in cotlib.go provides:
Eventstruct: The primary data structure representing a CoT message with XML marshaling/unmarshalingNewEvent(),NewPresenceEvent(): Event constructorsEventBuilder: Fluent API for constructing events withNewEventBuilder().WithContact().WithGroup().Build()UnmarshalXMLEvent(): Parses XML into Event with security limits and validationValidateType(),ValidateHow(),ValidateRelation(): Validation functions for CoT type codes- Event pooling via
getEvent()/ReleaseEvent()for reduced allocations
Subpackages
cottypes/: Type catalog system with ~10k CoT type definitionsCatalog: Thread-safe registry with zero-allocation lookupsgenerated_types.go: Auto-generated fromCoTtypes.xml(MITRE) andTAKtypes.xml(TAK extensions)GetCatalog(): Returns the singleton catalog instance- How/relation value mappings for position source and relationship types
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 · 90 lines · 902 tokens per session scan A a358c578c5a5
cotlib CLAUDE.md is an instructions file published in the GitHub repository NERVsystems/cotlib (11 stars, last pushed 1mo ago), licensed MIT. It adds 902 tokens to every session, about $0.0045 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 2026-08-30.
Other instructions, from other repositories
geolens AGENTS.md
Instructions for geolens-io/geolens, covering repository guidelines, project structure & module organization, build, test, and development commands, running a single test and working from a git worktree.
mazzap CLAUDE.md
Instructions for zymazza/mazzap, covering claude.md, what this is, commands, twin store and mcp server.
geolens CLAUDE.md
Instructions for geolens-io/geolens: This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
cesium-mcp copilot-instructions.md
Instructions for gaopengbin/cesium-mcp, covering 持续协作工作流, 概述, 每轮执行步骤, 协议同步工具调用规范 and 返回值解析.
cesium-mcp AGENTS.md
Instructions for gaopengbin/cesium-mcp, covering agents.md — cesium-mcp, monorepo structure, commands, code conventions and adding a new tool.
MIF copilot-instructions.md
Copilot instructions for modeled-information-format/MIF, covering mif project - copilot instructions, about this project, ontology management, quick commands and validate an ontology.