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 buildmoonshot/skillpacks --skill surgical-editsgit clone --depth 1 https://github.com/buildmoonshot/skillpacksWrote 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/buildmoonshot/skillpacks/surgical-edits)<a href="https://agentmods.dev/skills/buildmoonshot/skillpacks/surgical-edits"><img src="https://agentmods.dev/badge/skills/buildmoonshot/skillpacks/surgical-edits.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 | $0.00064 | $0.00451 |
| Opus 5 | $0.00032 | $0.00226 |
| Sonnet 5 | $0.00013 | $0.00090 |
| Haiku 4.5 | $0.00006 | $0.00045 |
Grade A, and why
surgical-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 7d 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.
What it actually says
Surgical Edits
When modifying existing code, change only what the task requires. Every line in your diff must trace directly back to the request.
Rules
-
Touch only what's required. Do not edit, reorder, or reformat code outside the scope of the task — even if you would normally write it differently.
-
Match the surrounding style. Mirror the existing naming, indentation, quote style, and comment density of the file you're editing, not your personal defaults.
-
No drive-by refactors. Do not rename variables, extract functions, restructure logic, or "clean up" adjacent code unless the task is explicitly about that. If you spot a real problem nearby, mention it — don't fix it.
-
No reformatting. Never let an auto-formatter or your own habits reflow lines you didn't functionally change. Whitespace-only churn hides the real change in review.
-
Clean up only your own mess. If your change makes an import, variable, or function unused, remove it. Do not remove pre-existing dead code unless asked.
-
Preserve what works. Keep existing comments, error handling, and edge-case logic unless the task is to change them.
Before acting, ask yourself
If a reviewer read this diff, would every changed line obviously connect to the request — or would they have to ask "why did you touch that?"
If any line would draw that question, revert it.
When the right fix IS a larger change
Sometimes the task genuinely requires broad changes (a real refactor, a migration). That's fine — but say so first: state what you're about to change and why it's in scope, then proceed. The rule isn't "never change a lot." It's "never change a lot silently."
What ships with it
1 file 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.
- 7d ago First seen · 33 lines · 64 tokens per session scan A 1a97702b485e
surgical-edits is a skill published in the GitHub repository buildmoonshot/skillpacks (2 stars, last pushed 2mo ago), licensed MIT. It adds 64 tokens to every session and 451 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
caliber-testing
Writes Vitest tests following project patterns: tests/ directories, vi.mock() for module mocking with vi.hoisted() for test-time factories, global LLM mock from src/test/setup.ts, environment variable save/restore in beforeEach/afterEach, vi.clearAllMocks() lifecycle, and test file organization. Use when user says…
scoring-checks
Add a new deterministic scoring check in src/scoring/checks/ that evaluates config quality. Follows the Check[] return pattern, uses point constants from src/scoring/constants.ts, and integrates via filterChecksForTarget() in src/scoring/index.ts. Use when user says 'add scoring check', 'new check', 'modify scoring…
writers-pattern
Add a new platform writer module in src/writers/ that generates and writes agent config files for a supported platform. Each writer exports a function that accepts a config interface, creates directories (rules/, skills/, mcp configs), writes files with proper formatting and frontmatter, and returns string[] of…
llm-provider
Adds a new LLM provider implementing LLMProvider interface with call() and stream() methods. Integrates with provider factory in src/llm/index.ts, config detection in src/llm/config.ts, and error handling via tracking and recovery. Use when adding a new model backend, integrating a third-party LLM API, or extending…
adding-a-command
Creates a new CLI command following the Commander.js pattern in src/commands/. Handles command registration in src/cli.ts, telemetry tracking via tracked() wrapper, and option parsing. Use when user says add command, new CLI command, create subcommand, or adds files to src/commands/. Do NOT use for modifying existing…
setup-caliber
Sets up Caliber for automatic AI agent context sync. Installs pre-commit hooks so CLAUDE.md, Cursor rules, and Copilot instructions update automatically on every commit. Use when Caliber hooks are not yet installed or when the user asks about keeping agent configs in sync.