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 monoes/monomind --skill pair-programminggit clone --depth 1 https://github.com/monoes/monomindWrote 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/monoes/monomind/pair-programming)<a href="https://agentmods.dev/skills/monoes/monomind/pair-programming"><img src="https://agentmods.dev/badge/skills/monoes/monomind/pair-programming/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/monoes/monomind/pair-programming"><img src="https://agentmods.dev/badge/skills/monoes/monomind/pair-programming.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 | $0.00039 | $0.01922 |
| Opus 5.5 | $0.00016 | $0.00769 |
| Sonnet 5.5 | $0.00008 | $0.00384 |
| Haiku 4.5 | $0.00004 | $0.00192 |
Grade A, and why
pair-programming 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 — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pair Programming
Collaborative pair programming where Claude acts as your partner in a defined role. The CLI has no pair command: the session lives in the conversation. Claude uses its normal tools (Read, Edit, Bash, the Task tool) plus real monomind commands for task tracking, shared memory, and continuity across sessions.
What This Skill Does
- Role management: Claude takes a clear role (driver, navigator, reviewer, mentor) and switches when asked
- Continuous review: every change is reviewed for correctness, security, and readability before moving on
- Test discipline: tests run after each meaningful change; TDD sessions write failing tests first
- Specialist help: Claude can spawn Task-tool agents (tester, reviewer, Security Engineer) for focused checks
- Continuity: decisions go into
monomind memory; outcomes go intomonomind hooksso routing learns
Prerequisites
Required:
- Claude Code
- Git repository (recommended, so every step can be diffed and reverted)
Optional:
- Monomind CLI (
npm install -g monomind@latest, ornpx monomind) for tracking and memory - Test framework, linter, and formatter configured in the project
Quick Start
Tell Claude the goal and the role:
"Pair with me on JWT auth. You navigate: I write the code, you review each piece and flag issues."
"Pair with me on the shopping cart, TDD. You write the failing tests first, I implement."
Optionally register the task so the hooks system can suggest agents and record the outcome:
npx monomind hooks pre-task --description "Pair: implement JWT auth" --task-id pair-jwt
Roles and Modes
Driver (Claude writes, you guide)
Claude writes the code with Edit/Write; you set direction and approve each step.
Claude's protocol:
- State the plan for the next small step (one function, one endpoint)
- Implement it
- Run the relevant tests or build
- Show the diff and wait for your review before the next step
Best for: scaffolding, boilerplate, rapid prototyping, exploring an unfamiliar library.
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 · 230 lines · 39 tokens per session scan A c1d58b49bfe5
pair-programming is a skill published in the GitHub repository monoes/monomind (23 stars, last pushed 2d ago), licensed Apache-2.0. It adds 39 tokens to every session and 1,922 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 2026-10-26.
Other skills, from other repositories
hk-rca
Interactive Root Cause Analysis enforcer. Guides you through the 7-step RCA protocol: Reproduce, Locate, Hypothesis, Failing Test, Fix, Verify Live, Document. Use when debugging a bug, investigating a failure, or when something unexpected happened. This skill gates each step — it won't let you skip to a fix without…
build-test
Run the project's build / typecheck / lint / test commands and emit the build.passing + tests.passing signals devloop convergence reads.
resolve-author-fix
Find the root cause, implement a focused fix, and prove behavior with targeted tests and recordings.
diag-harness
Kernel-version skew check (ADR-027). Reports manifest surface + manifest kernel + installed kernel + verdict (match/patch-diff/minor-diff/major-diff). Exits 1 on minor/major skew with a copy-pasteable npm install @metaharness/[email protected] next step. Exits 2 if no .harness/manifest.json at path.
score-harness
5-dimension scorecard (0-100, grade A/B/C/F) for a scaffolded harness. Dimensions: Repo understanding (25%), Agent usefulness (25%), MCP safety (20%), Test coverage (15%), Publish readiness (15%). Emits a 6-field badges block (score + mcpRisk + 4 booleans) ready for the harness README. Exit 0 A/B, 1 C, 2 F.
validate-fix
Prove a fix works before declaring done — re-run the failing test, run the full suite, typecheck, lint, and harden against recurrence. Use after implementing a bug fix, when user says "is this fixed?", or before closing an investigation.