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/lossless-claude/lcm/copilot-instructionsgit clone --depth 1 https://github.com/lossless-claude/lcmWrote 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/lossless-claude/lcm/copilot-instructions)<a href="https://agentmods.dev/instructions/lossless-claude/lcm/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/lossless-claude/lcm/copilot-instructions.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 | $0.00618 | $0.00618 |
| Opus 5 | $0.00309 | $0.00309 |
| Sonnet 5 | $0.00124 | $0.00124 |
| Haiku 4.5 | $0.00062 | $0.00062 |
Grade A, and why
lcm copilot-instructions.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 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot Review Instructions — lossless-claude (lcm)
This repo is a TypeScript SQLite daemon that persists Claude session memories across context resets. It uses Node.js DatabaseSync (synchronous SQLite API) and exposes an HTTP daemon with REST routes.
Primary concerns
Database connection pattern (highest priority)
- All SQLite access MUST use
getLcmConnection()andcloseLcmConnection()from the shared connection module. Flag anynew DatabaseSync(...)instantiated directly in route handlers or utility files. - The shared connection ensures WAL mode and foreign key enforcement are set once at open time.
- Flag double-open patterns: calling
getLcmConnection()without a correspondingcloseLcmConnection()on all exit paths.
PRAGMA enforcement
- If a new connection is ever opened directly (e.g., in migration scripts), it must immediately set:
PRAGMA journal_mode=WALPRAGMA foreign_keys=ON
- Flag connections missing these PRAGMAs.
Type safety
- No implicit
any. All function parameters, return types, and object shapes must be explicitly typed. - Flag
as anycasts unless accompanied by a comment explaining why it's necessary. - Route handler request/response objects must use typed interfaces, not
any.
collectStats() performance
collectStats()takes ~13 seconds due to full-table scans. It must NEVER be called in:- HTTP request handlers
- Any path that runs more than once per user action
- Startup initialization (lazy evaluation only)
- Flag any
collectStats()call that isn't in a dedicated stats endpoint or background job.
Test coverage
- New HTTP routes must have corresponding tests in
test/daemon/routes/. - Tests should cover: happy path, missing required fields (400), and resource-not-found (404).
- Flag PRs adding routes without tests.
SQLite transaction safety
- Any operation that modifies more than one table must be wrapped in
BEGIN/COMMIT. - Flag multi-table writes without transactions — they risk partial writes on crash.
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 · 52 lines · 618 tokens per session scan A 0ef3bbed41d5
lcm copilot-instructions.md is an instructions file published in the GitHub repository lossless-claude/lcm (24 stars, last pushed yesterday), licensed MIT. It adds 618 tokens to every session, about $0.0031 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
vespertide AGENTS.md
AGENTS.md instructions for dev-five-git/vespertide, covering vespertide knowledge base, structure, where to look, data flow and conventions.
lms-front CLAUDE.md
Claude Code instructions for guillermoscript/lms-front, covering claude.md, project overview, commands, architecture and multi-tenancy.
rails_ai_agents AGENTS.md
AGENTS.md instructions for ThibautBaissac/rails_ai_agents, covering project configuration, tech stack, architecture, key commands and tests.
seekstone CLAUDE.md
Instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.
pg-dash CLAUDE.md
Claude Code instructions for indiekitai/pg-dash, covering pg-dash claude.md, 项目结构, 构建与测试, 发版纪律(强制) and 发版检查清单(每次 npm publish 前必须按序执行).
MCP-SqlServer CLAUDE.md
Claude Code instructions for Aron-Valenzuela/MCP-SqlServer, covering claude.md, project overview, setup (for each user), 1. install dependencies and 2. configure claude desktop.