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 levnikolaevich/claude-code-skills --skill ln-35-surgical-change-implementergit clone --depth 1 https://github.com/levnikolaevich/claude-code-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/levnikolaevich/claude-code-skills/ln-35-surgical-change-implementer)<a href="https://agentmods.dev/skills/levnikolaevich/claude-code-skills/ln-35-surgical-change-implementer"><img src="https://agentmods.dev/badge/skills/levnikolaevich/claude-code-skills/ln-35-surgical-change-implementer/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/levnikolaevich/claude-code-skills/ln-35-surgical-change-implementer"><img src="https://agentmods.dev/badge/skills/levnikolaevich/claude-code-skills/ln-35-surgical-change-implementer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
SkillSpector: 1 finding, up to low
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- low Excessive Agency · line 45 Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
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 | $0.00037 | $0.02600 |
| Opus 5 | $0.00018 | $0.01300 |
| Sonnet 5 | $0.00007 | $0.00520 |
| Haiku 4.5 | $0.00004 | $0.00260 |
Grade A, and why
ln-35-surgical-change-implementer 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 6d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Surgical Change Implementer
Goal: Deliver one approved product-code change through the smallest complete solution that satisfies the business outcome. Remove superseded code and avoid speculative abstraction, duplicate mechanisms, and custom infrastructure already provided by the repository or platform.
Execution contract: The ordered checkboxes are the Definition of Done. Track every item internally as PENDING, PROVEN with concrete evidence, CLEARED with evidence that its condition is absent, or UNPROVEN with a gap; reading, delegation, or tool failure is not proof. Reconcile items after each section. Before returning, resolve all PENDING and count only PROVEN and CLEARED; apply the skill's verdict and approval rules to every gap.
Preserve user intent, scope, and existing authorization. Continue authorized work; ask only for consequential unresolved choices or required external approval. Scale depth to material risk without silently skipping checks. Preserve dependency and safety ordering; otherwise choose the verification method appropriate to each obligation.
Tool Routing
| Need | Preferred capability | Fallback |
|---|---|---|
| Scope and repository policy | User request, linked task or plan, repository instructions, Git status, and focused diff | State bounded assumptions; stop if a choice would materially change product intent |
| Runtime ownership and impact | Language server, host-native code intelligence, traces, schemas, routes, and configuration | Narrow symbol and text search followed by direct reads of definitions and consumers |
| Existing capability | Repository code, manifests, lockfiles, platform APIs, and installed dependency source | Current official documentation and primary sources; mark uncertain claims UNVERIFIED |
| Safe implementation | Focused editor, native formatter, package manager, and generation commands | Minimal manual patch that preserves user changes and generated-file ownership |
| Verification | Repository-defined build, lint, type, test, smoke, and runtime checks | Smallest reproducible check that proves the protected contract; disclose coverage gaps |
| External semantics | Official documentation, specifications, security advisories, registries, and upstream source | Primary-source technical material; use secondary expert guidance only for tradeoffs |
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.
- 6d ago Changed · -13 lines · -9 tokens per session bd4082d55d16
- 13d ago First seen · 121 lines · 46 tokens per session scan A a7f021bab60c
ln-35-surgical-change-implementer is a skill published in the GitHub repository levnikolaevich/claude-code-skills (559 stars, last pushed 7d ago), licensed MIT. It adds 37 tokens to every session and 2,600 once invoked, about $0.0002 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 skills, from other repositories
dev-rc
The last gate before merge — QA, security audit, review and changelog, with objective pass conditions.
triage-report
Drain the .review/ report queue. Resolves un-triaged scan/audit reports (producer-agnostic — check-docs-consistency and any other scanner), dispatches the triage-report subagent (Sonnet) one report at a time for per-finding dispositions (promote / patch / dup / needs-investigation / dismiss), then the gateway absorbs…
solid-principles
SOLID principles checklist with Java examples. Use when a class has too many responsibilities, an abstraction leaks, or a dependency points the wrong way, and when the user asks about Single Responsibility, Open/Closed, Liskov, Interface Segregation or Dependency Inversion. For naming, duplication and method length…
architecture-review
Analyze Java project architecture at macro level - package structure, module boundaries, dependency direction, and layering. Use when user asks "review architecture", "check structure", "package organization", or when evaluating if a codebase follows clean architecture principles.
java-code-review
Systematic code review for Java with null safety, exception handling, concurrency, and performance checks. Use when user says "review code", "check this PR", "code review", or before merging changes.
review-loop
Run the adversarial verification loop — implement, then hand the change to a fresh checker that did not write it, fix what it finds, and re-dispatch until APPROVE. Use before claiming any behavioural change is done, and on requests like "review loop", "adversarial review", "independent review", "get this verified"…