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 oyi77/1ai-skills --skill codinggit clone --depth 1 https://github.com/oyi77/1ai-skillsWrote 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/oyi77/1ai-skills/coding)<a href="https://agentmods.dev/skills/oyi77/1ai-skills/coding"><img src="https://agentmods.dev/badge/skills/oyi77/1ai-skills/coding/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/oyi77/1ai-skills/coding"><img src="https://agentmods.dev/badge/skills/oyi77/1ai-skills/coding.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00054 | $0.03450 |
| Opus 5.5 | $0.00022 | $0.01380 |
| Sonnet 5.5 | $0.00011 | $0.00690 |
| Haiku 4.5 | $0.00005 | $0.00345 |
Grade A, and why
coding 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 1mo 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
result = subprocess.run(cmd, capture_output=True, text=True) How it starts
The opening of the file, as written. The whole thing — 388 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
This skill is the hub for five specialized coding agents — linter, perf, refactor, security, and test — each owning one discipline on the same codebase. Load it when a change touches quality across multiple dimensions and you want each concern handled by an expert pass. It routes each agent in sequence so the passes compose instead of collide.
Coding Agents
Money-Making Overview
| Agent | Revenue Impact | Avg. Savings | Best For |
|---|---|---|---|
| Linter Agent | Enforces standards at scale | $300–1,000/project | Bulk rule application, migration, cleanup |
| Perf Agent | Cuts infra costs 20–40% | $2,000–20,000/year | Bottleneck profiling, query tuning, cost reduction |
| Refactor Agent | Reduces maintenance debt 50% | $3,000–15,000/refactor | Complexity reduction, modernization, splitting monoliths |
| Security Agent | Prevents P1 production incidents | $5,000–50,000/incident | Bug bounty, vulnerability scanning, pentest automation |
| Test Agent | Cuts regression bugs 80% | $2,000–8,000/release | Coverage gaps, regression tests, e2e flows |
Combined ROI: A single pass through all five agents on a medium codebase (50K LOC) saves $15,000–50,000 by preventing production bugs, reducing cloud costs, and slashing maintenance overhead.
When to Use
Linter first — before every PR, after merge conflicts, when adopting new rules, migrating linters.
Perf when it hurts — app is slow, memory is growing, queries lag, infra costs too high, capacity planning.
Refactor before features — make the change easy before making the easy change. High cyclomatic complexity, duplicated code, monolithic files.
Security before deploy — every commit touching auth, payments, PII, or external APIs requires a security gate.
Test always — new features (TDD), regression tests for bugs, coverage gaps, integration tests, e2e.
When NOT to Use
- Trivial one-liner changes — just make the edit.
- Real-time human judgment — agents cannot decide product or business trade-offs.
- Agent lacks access to required tools, credentials, or data.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago Changed · +11 lines e6a11e1f7a0e
- 1mo ago First seen · 377 lines · 54 tokens per session scan A 7ffeb6137022
coding is a skill published in the GitHub repository oyi77/1ai-skills (16 stars, last pushed today), licensed MIT. It adds 54 tokens to every session and 3,450 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
sage-review
Deep, platform-neutral code review for PRs and CRs in ONE thorough single pass — design reasoning (Problem Worth Solving & Solution Fit) as one dimension alongside the 9 code-level dimensions, with chain-of-consequences, self-critique, and draft-only comments. The single app-owned source of truth.
review
Review a small code change for correctness and missing tests.
plugin-test
A testing guide for Zhin.js plugins using Vitest, a JavaScript and TypeScript testing framework. It focuses on checking command and tool behavior, ordinary business logic, and the plugin package’s required structure.
prune
Run all quality lenses (validate, simplify), aggregate findings into a design doc, then drive the full feature chain (PRD → TDD → PR) to fix them systematically.
code-reviewer
A code-review workflow written in Chinese that checks software changes for correctness, security, performance, and maintainability. It also defines a report format for critical issues and suggestions.
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.