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 agentmods add skills/codewithmukesh/dotnet-claude-kit/build-fixnpx skills add codewithmukesh/dotnet-claude-kit --skill build-fixgit clone --depth 1 https://github.com/codewithmukesh/dotnet-claude-kitWhat 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 | $0.00146 | $0.01782 |
| Opus 5 | $0.00073 | $0.00891 |
| Sonnet 5 | $0.00029 | $0.00356 |
| Haiku 4.5 | $0.00015 | $0.00178 |
Grade A, and why
build-fix 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 yesterday.
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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/build-fix
What
The kit's autonomous iteration-loop skill. It drives a broken dotnet build
(or failing dotnet test) to green by looping: run, parse failures,
categorize by root cause, apply targeted fixes, re-run. It repeats until
green or a guard fires — the same way an experienced developer works through
a wall of red, but with hard limits that stop it from thrashing.
This is not a single-pass fix. It handles cascading errors where fixing one issue reveals the next.
When
- The build is broken and there are multiple compiler errors
- Tests are failing after code changes or a build-fix pass
- After a major refactor that touched type names, namespaces, or signatures
- After updating NuGet packages (especially major version bumps)
- After merging a branch with conflicts resolved but not compiled
- After scaffolding or code generation that needs manual adjustments
- User says: "fix the build", "make it compile", "make the tests pass", "keep going until it works", "keep fixing"
How
Loop Discipline (applies to every loop)
- Bounded iteration, always — Default max 5 iterations, hard cap 10 (user "keep going" extends by 3, never past 10). If 5 iterations cannot solve it, the problem needs human judgment, not a 6th identical attempt.
- Progress or exit — Each iteration must reduce the error/failure count. Same errors after a fix attempt = STUCK: stop, report, and re-plan with a different approach. Never retry the same fix that already failed.
- Categorize before fixing — Group errors by root cause and fix the
highest-leverage first (one missing
usingcan erase a dozen downstream errors). - Transparency per iteration — Report what changed and why:
Iteration 3/5: fixed CS0246 by adding using System.Text.Json, 2 remain. Never modify files silently. - Atomicity — Each iteration leaves the codebase no worse than before. If iteration 3 fails, the code stays in iteration 2's state.
Primary Flow: Build-Fix Loop (max 5 iterations)
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.
- yesterday First seen · 162 lines · 146 tokens per session scan A ab682e444492
build-fix is a skill published in the GitHub repository codewithmukesh/dotnet-claude-kit (684 stars, last pushed 25d ago), licensed MIT. It adds 146 tokens to every session and 1,782 once invoked, about $0.0007 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…