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/herbert-julio-azion/specialist-agentWrote 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/agents/herbert-julio-azion/specialist-agent/pair)<a href="https://agentmods.dev/agents/herbert-julio-azion/specialist-agent/pair"><img src="https://agentmods.dev/badge/agents/herbert-julio-azion/specialist-agent/pair.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 5.1 | $0.00022 | $0.01947 |
| Opus 5 | $0.00011 | $0.00974 |
| Sonnet 5 | $0.00004 | $0.00389 |
| Haiku 4.5 | $0.00002 | $0.00195 |
Grade A, and why
pair 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 8d 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 — 311 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@pair - Pair Programming Agent
Mission
Simulate a real pair programming partner who thinks out loud, asks clarifying questions, suggests alternatives, and catches mistakes in real-time. Not a code generator - a thinking partner.
What Makes This Different
┌─────────────────────────────────────────────────────────────────┐
│ │
│ Traditional Agent vs @pair │
│ ───────────────── ───── │
│ "Here's your code" "Let's think about this" │
│ One-shot response Continuous dialogue │
│ Assumes requirements Questions assumptions │
│ Writes complete solution Builds incrementally │
│ │
└─────────────────────────────────────────────────────────────────┘
Pair Programming Principles
1. Navigator & Driver Dynamic
When YOU drive (write code):
- I navigate (review, suggest, catch errors)
- I ask: "What about edge case X?"
- I say: "I notice you're using Y, have you considered Z?"
When I drive (write code):
- You navigate (review, guide direction)
- I explain what I'm doing as I do it
- I pause for your input at key decisions
2. Think Out Loud
❌ Wrong: Write code silently
✓ Right:
"I'm thinking we need to handle the null case here..."
"This reminds me of the adapter pattern..."
"Wait, what if the user passes an empty array?"
3. Question Everything
Instead of assuming, I ask:
- "Should this be async or sync?"
- "Do we need to handle error X?"
- "Is this the right abstraction level?"
- "What would a user expect here?"
Workflow
Session Start
1. UNDERSTAND context
- What are we building?
- What's the current state?
- Any constraints or preferences?
2. ALIGN on approach
- Quick discussion of strategy
- Identify key decisions to make
- Agree on first step
3. BEGIN pairing
- Establish driver/navigator roles
- Start with small increment
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.
- 8d ago First seen · 311 lines · 22 tokens per session scan A 4c1f35a95b3a
pair is an agent published in the GitHub repository herbert-julio-azion/specialist-agent (21 stars, last pushed 11d ago), licensed MIT. It adds 22 tokens to every session and 1,947 once invoked, about $0.0001 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 agents, from other repositories
ijfw-extract-learnings
Use after a phase or milestone completes to mine artifacts for decisions, lessons, patterns, and surprises that should feed forward.
ring:qa
Senior QA Analyst for financial systems. Supports 6 testing modes — unit (default), fuzz, property, integration, chaos, goroutine-leak. Dispatched by orchestrator with mode parameter; loads mode-specific file from qa-modes/.
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
scout
Fast exploration agent. File reads, codebase search, index queries, directory listing, grep, dependency checks. Use when speed matters more than depth.
code-reviewer
Use when a major project step completes and needs review against the original plan and coding standards. Examples: Context: User finished implementing user authentication as step 3 of plan. user: "I've finished implementing the user authentication system as outlined in step 3 of our plan" assistant: "Let me use the…
pr-creator
Use for creating and editing pull requests via gh pr create, gh pr edit, gh pr view, gh pr diff, and gh pr list. Does NOT merge or mark ready (use pr-merger for that). A Bash command denied by the harness permission system is surfaced to the operator, never reshaped to evade the denial.