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 alivirgo/Major-AI-Skills --skill atomic-code-editsgit clone --depth 1 https://github.com/alivirgo/Major-AI-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/alivirgo/major-ai-skills/atomic-code-edits)<a href="https://agentmods.dev/skills/alivirgo/major-ai-skills/atomic-code-edits"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/atomic-code-edits/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/alivirgo/major-ai-skills/atomic-code-edits"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/atomic-code-edits.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 | $0.00026 | $0.01304 |
| Opus 5.5 | $0.00010 | $0.00522 |
| Sonnet 5.5 | $0.00005 | $0.00261 |
| Haiku 4.5 | $0.00003 | $0.00130 |
Grade A, and why
atomic-code-edits 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 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.
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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Atomic Code Edits (Targeted Differential Patching)
Overview
When modifying existing source files, naive agents rewrite the entire file from line 1 to line 800 using tools like write_to_file.
Full-file overwrites suffer from three catastrophic failure modes:
- The Truncation Disaster: The model outputs
// ... rest of existing code remains unchanged ..., permanently deleting critical business logic. - Extreme Token Waste: Modifying a 1-line boolean flag in an 800-line file generates 3,000+ output tokens instead of 30 tokens.
- Severe Generation Latency: Streaming an entire file takes 15 to 25 seconds per edit turn, slowing down developer feedback loops.
The Atomic Code Edit Protocol enforces targeted differential patching using character-exact substring replacement tools (replace_file_content, multi_replace_file_content).
Full-File Overwrite vs. Atomic Differential Patch
┌─────────────────────────────────────────────────────────────┐
│ Code Mutation Token Economics │
│ │
│ Full File Overwrite (`write_to_file`): │
│ • Agent regenerates all 650 lines │
│ • 2,800 Output Tokens streamed │
│ • 18.2 Seconds Latency │
│ • High risk of comment/type erasure │
│ │
│ Atomic Patch (`replace_file_content`): │
│ • Agent targets lines 142-146 only │
│ • 35 Output Tokens streamed │
│ • 0.4 Seconds Latency (45x Faster!) │
│ • 100% Codebase Integrity Guaranteed │
└─────────────────────────────────────────────────────────────┘
The 4 Rules of Precision Atomic Editing
1. Tight Line Bounding (StartLine / EndLine)
Specify the smallest possible line range containing the target code (e.g., StartLine: 140, EndLine: 148). This confines the search window, preventing accidental replacement of duplicate variable names elsewhere in the file.
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 · -13 tokens per session f3888d9c8e09
- 1mo ago First seen · 133 lines · 39 tokens per session scan A 7c4e9b581f45
atomic-code-edits is a skill published in the GitHub repository alivirgo/Major-AI-Skills (2 stars, last pushed today), licensed MIT. It adds 26 tokens to every session and 1,304 once invoked, about $0.0001 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 2026-09-05.
Other skills, from other repositories
agenttrace-session-audit
Audit local AI coding-agent sessions with agenttrace for cost, tool failures, latency, anomalies, health, diffs, and CI gates.
eval-hooks
Audit Claude Code and Codex hooks for validity, safety, and correctness across settings.json, hooks.json, config.toml, plugin, and skill or agent frontmatter hooks. Resolves each command, checks event names, handler types, matchers, exit-code and JSON decision strategy, and timeouts against each host's documented…
check-cache-bugs
Audit Claude Code setup for cache bugs (CC#40524): sentinel, --resume/--continue, attribution header + ArkNill B3/B4/B5.
sandbox-unblock
Diagnostic protocol to run before reporting a sandbox blocker or asking for a configuration change. Eleven checks that eliminate false positives, then a report template the person holding the settings can act on. On one measured day, six of eight reported blockers turned out to be false, all from the same handful of…
investigate
Systematic root-cause debugging: find the cause before writing any fix.
qa
Systematic QA testing of a web application: diff-aware, tiered, with fix-and-verify loop.