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/merencia/pairwith/agents-mdgit clone --depth 1 https://github.com/merencia/pairwithWhat 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 | $0.00686 | $0.00686 |
| Opus 5 | $0.00343 | $0.00343 |
| Sonnet 5 | $0.00137 | $0.00137 |
| Haiku 4.5 | $0.00069 | $0.00069 |
Grade A, and why
pairwith AGENTS.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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Ground rules for any agent (or human) working in this repo. Read this before editing anything.
What this repo is
An open-source CLI (pairwith) plus a registry of developer style profiles — Markdown files that shape how an AI coding assistant communicates, reasons about trade-offs, and frames feedback. A profile is inspired by publicly observable aspects of a specific developer's technical work. It is not the real person and does not represent them.
- The CLI is infrastructure: it must be small, predictable, and safe.
- Profiles are community content: they must pass quality, consent, and non-impersonation checks. See
PROFILE_POLICY.mdandDISCLAIMER.md.
Pair programming rules
- Don't edit code without explicit confirmation.
- Before acting, state briefly what will change, where, and why.
- Work in small steps. Don't make changes outside the requested scope.
- Ask when genuinely unsure. Don't guess at contracts (command names, flags, output format).
Test-first when there's an issue
When working from an issue: write the tests first, open a draft PR with just the tests, get alignment, then implement. Skip this flow for trivial changes.
CLI UX (non-negotiable)
- Success output →
stdout. Errors and progress →stderr. - Exit
0on success,1on user error (bad input, not found),2on unexpected error. - User errors get a clear, actionable message. No stack traces unless
--verbose. --helpis authoritative documentation — keep it current.- Respect
NO_COLOR. Don't assume Unicode support.
Safety
- A profile is a prompt. The CLI never executes profile content — it only writes files.
- By default, only write under
~/.claude/agents/,~/.claude/skills/,~/.copilot/agents/,~/.copilot/skills/, or~/.cursor/rules/, unless the user passes--pathexplicitly. - Never overwrite an existing file without confirmation, unless
--force. - Every network call has a timeout and a size limit. Sanitize any handle/URL before using it.
- Never log tokens, credentials, or third-party transcript content.
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 · 56 lines · 686 tokens per session scan A 0304de651908
pairwith AGENTS.md is an instructions file published in the GitHub repository merencia/pairwith (7 stars, last pushed 4mo ago), licensed MIT. It adds 686 tokens to every session, about $0.0034 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 instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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
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, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.