Borrowing it
Nothing to install: this file belongs to viames/pair. 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/viames/pair/main/AGENTS.mdgit clone --depth 1 https://github.com/viames/pairWrote 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/viames/pair/agents-md)<a href="https://agentmods.dev/instructions/viames/pair/agents-md"><img src="https://agentmods.dev/badge/instructions/viames/pair/agents-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/viames/pair/agents-md"><img src="https://agentmods.dev/badge/instructions/viames/pair/agents-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 | $0.01503 | $0.01503 |
| Opus 5.5 | $0.00601 | $0.00601 |
| Sonnet 5.5 | $0.00301 | $0.00301 |
| Haiku 4.5 | $0.00150 | $0.00150 |
Grade A, and why
pair AGENTS.md scanned grade A with 1 finding 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 today.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Required Composer extensions: `curl`, `intl`, `json`, `mbstring`, `PDO` and How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Pair Framework v4
Primary entrypoint for automated agents working on this repository. Read this first, then SKILL.md for the source map and local commands. Do not add agent-specific shim files unless they contain genuinely non-duplicated operational requirements.
The default branch implements and documents Pair v4, the stable line used by
the maintainer's applications. The v3 branch is the previous maintenance line;
v4 guidance may not apply to it.
Mission
Make small, safe, reviewable changes consistent with existing Pair architecture. Preserve backward compatibility unless explicitly asked otherwise. When guidance conflicts, favor the smallest safe change aligned with existing patterns and the precedence below.
Workflow
Before making any change:
- Inspect
src/to understand the namespace layout. - Find the closest component solving a similar problem and read at least one full class in it.
- Check for existing utilities before creating helpers or architectural patterns.
- Inspect
tests/to understand expected behavior. - Verify public API usage before modifying framework classes.
Then:
- Implement the smallest change in the owning component, following nearby code and the conventions below.
- Add or update deterministic tests when behavior changes. Never modify tests merely to make a broken implementation pass.
- Run relevant checks and verify compatibility, security and performance. If tests are absent, use the closest manual/local validation and report that limit.
- Update the owning documentation when commands, configuration or public
behavior change; public framework changes require the relevant sibling
pair.wikipages, especially API and.envreferences. - Review the diff for unrelated files, dependencies and secrets, then report the result using the completion format below.
For an ambiguous or overly broad request, or one risking an architectural or compatibility mistake, ask for clarification before changing code.
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.
- today First seen · 159 lines · 1,503 tokens per session scan A 7f387bec7c54
pair AGENTS.md is an instructions file published in the GitHub repository viames/pair (11 stars, last pushed 3d ago), licensed MIT. It adds 1,503 tokens to every session, about $0.0060 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-15.
pair AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| pair AGENTS.mdviames/pair | Instructions file | 11 | 3d ago | MIT | A | 1,503 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 144k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,685 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 150k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,086 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 282k | 3d ago | MIT | A | 4,335 | Codex, OpenCode |