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 skills add logicrw/agpair --skill claudegit clone --depth 1 https://github.com/logicrw/agpairWrote 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/skills/logicrw/agpair/claude)<a href="https://agentmods.dev/skills/logicrw/agpair/claude"><img src="https://agentmods.dev/badge/skills/logicrw/agpair/claude/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/skills/logicrw/agpair/claude"><img src="https://agentmods.dev/badge/skills/logicrw/agpair/claude.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 | $0.00046 | $0.03985 |
| Opus 5.5 | $0.00018 | $0.01594 |
| Sonnet 5.5 | $0.00009 | $0.00797 |
| Haiku 4.5 | $0.00005 | $0.00398 |
Grade A, and why
agpair 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 2mo 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 — 348 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGPair for Claude Code
IRON LAW: Non-trivial work requires an explicit routing budget. Use external AGPair lanes by default, but fan out only when each lane has a distinct role, scope, hypothesis, or verification value. Multiple grok-cli lanes are valid when they are not duplicate prompts.
Claude Code is the controller and verifier. AGPair is the durable external-agent control plane.
Default Route
Use AGPair before Claude Code native subagents for non-trivial implementation, refactor, test-fix, research, review, or multi-file work.
Actively outsource low-value, repetitive, time-consuming, or easily verifiable work through AGPair: repo scans, alternative reviews, focused test-fix attempts, multi-file mechanical edits, smoke checks, and implementation slices with clear acceptance criteria. For ordinary non-trivial work, start with a strong external lane: grok-cli and antigravity-cli are peer first choices. Use both when independent evidence, implementation contrast, or latency hedging is useful. It is acceptable to run several attempts from the same executor at once for parallel review, competing implementation approaches, or file-sliced work, but each attempt needs a distinct task id, role, prompt, or scope.
Prefer these external lanes:
grok-cliandantigravity-clias peer first choices for review, research, and implementation attempts.- Additional
grok-cliorantigravity-clilanes when prompts, scopes, or acceptance criteria are distinct. codexwhen an AGPair-managed external Codex CLI worker is useful as a fallback or challenger executor.
codex is the AGPair-managed external Codex CLI worker for Claude Code controllers. It is the cross-controller fallback lane, not a Claude Code native subagent.
Do not request the AGPair-managed external claude-code executor by default; Claude Code already has native subagents and claude-code is suppressed for Claude Code controllers unless --allow-self-executor is explicitly justified.
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.
- 2mo ago First seen · 348 lines · 46 tokens per session scan A 0d4da411809e
agpair is a skill published in the GitHub repository logicrw/agpair (50 stars, last pushed 4mo ago), licensed MIT. It adds 46 tokens to every session and 3,985 once invoked, about $0.0002 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.
agpair compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| agpairlogicrw/agpair | Skill | 50 | 4mo ago | MIT | A | 46 | Claude Code |
| feishuHmbown/CodeWhale | Skill | 41k | yesterday | MIT | A | 33 | Claude Code, Codex |
| interviewHmbown/CodeWhale | Skill | 41k | yesterday | MIT | A | 40 | Claude Code, Codex |
| refocusingmvschwarz/openrig | Skill | 8.8k | today | Apache-2.0 | A | 59 | Claude Code |
| recipe-create-meet-spacegoogleworkspace/cli | Skill | 32k | 7d ago | Apache-2.0 | A | 18 | Claude Code, Codex |
| printing-press-importmvanhorn/cli-printing-press | Skill | 4.9k | today | MIT | A | 104 | Claude Code |
| atmos-validationcloudposse/atmos | Skill | 1.4k | today | Apache-2.0 | A | 31 | Claude Code |