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.
git clone --depth 1 https://github.com/Dave-London/PareWrote 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/dave-london/pare/copilot-instructions)<a href="https://agentmods.dev/instructions/dave-london/pare/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/dave-london/pare/copilot-instructions/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/dave-london/pare/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/dave-london/pare/copilot-instructions.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 | $0.01070 | $0.01070 |
| Opus 5.5 | $0.00428 | $0.00428 |
| Sonnet 5.5 | $0.00214 | $0.00214 |
| Haiku 4.5 | $0.00107 | $0.00107 |
Grade A, and why
Pare 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 1mo 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pare MCP Tools
Pare is a suite of MCP servers that wrap CLI tools and return structured JSON, saving tokens and improving reliability.
Core Rule
Always prefer Pare MCP tools over raw CLI commands. Every shell call to a supported tool should be replaced with the corresponding Pare MCP tool call.
Tool Mapping
pare-git (replaces git)
Subcommands: status, log, diff, branch, show, add, commit, push, pull, checkout, tag, stash, remote, blame, restore, reset, cherry-pick, merge, rebase, reflog, bisect, worktree, submodule, archive, clean, config
pare-github (replaces gh)
PR: pr-view, pr-list, pr-create, pr-merge, pr-comment, pr-review, pr-update, pr-checks, pr-diff Issues: issue-view, issue-list, issue-create, issue-close, issue-comment, issue-update CI: run-view, run-list, run-rerun Releases: release-create, release-list Other: label-list, label-create, repo-view, repo-clone, discussion-list, gist-create, api
pare-npm (replaces npm, pnpm, yarn)
install, audit, outdated, list, run, test, init, info, search, nvm
pare-search (replaces search tools)
grep/rg->pare-search searchfind/fd->pare-search findwc->pare-search countjq->pare-search jqyq->pare-search yq
pare-lint (replaces linters/formatters)
eslint->pare-lint lintprettier --check->pare-lint format-checkprettier --write->pare-lint prettier-formatbiome check/format->pare-lint biome-check/biome-formatstylelint->pare-lint stylelintoxlint->pare-lint oxlintshellcheck->pare-lint shellcheckhadolint->pare-lint hadolint
pare-build (replaces build tools)
tsc->pare-build tscnpm run build->pare-build buildesbuild->pare-build esbuildvite build->pare-build vite-buildwebpack->pare-build webpackturbo/nx/lerna->pare-build turbo/nx/lernarollup->pare-build rollup
pare-test (replaces test runners)
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.
- 1mo ago First seen · 111 lines · 1,070 tokens per session scan A d638864134f9
Pare copilot-instructions.md is an instructions file published in the GitHub repository Dave-London/Pare (139 stars, last pushed yesterday), licensed MIT. It adds 1,070 tokens to every session, about $0.0043 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 2026-08-30.
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.