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/jotjunior/cstk/bugfixnpx skills add JotJunior/cstk --skill bugfixgit clone --depth 1 https://github.com/JotJunior/cstkWhat 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 | $0.00054 | $0.02553 |
| Opus 5 | $0.00027 | $0.01277 |
| Sonnet 5 | $0.00011 | $0.00511 |
| Haiku 4.5 | $0.00005 | $0.00255 |
Grade C, and why
bugfix scanned grade C 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 2d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
# Node: rm -rf node_modules/.cache && npm run build How it starts
The opening of the file, as written. The whole thing — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bug Fix Skill
Structured bug fix protocol designed to eliminate cascading fix-reveal-fix cycles by mapping the full data flow before touching any layer. Stack-agnostic — adapt the commands and layer names to the project you are working in.
Arguments
$ARGUMENTS should describe the bug: error message, observed behavior, expected behavior, or path to a screenshot.
Step 0: Determine Complexity
Assess bug scope before starting:
| Complexity | Signals | Approach |
|---|---|---|
| Single-layer | Error in one file, one service | Sequential trace (Steps 1-8) |
| Multi-service | DTOs, enums, or events cross service boundaries | Parallel agent investigation (Step 3b) |
| Ghost bug | "Works on my machine", intermittent, post-deploy | Stale artifact focus (Step 2) |
For multi-service bugs, create tasks to track progress across services.
Step 1: Understand the Bug
- Read the error message or user description carefully
- Identify which service/layer reported the error
- If a screenshot was provided, analyze it
- Ask which layer owns the responsibility before assuming where the fix goes
- For frontend-reported bugs: verify whether the fix should be backend-side first — the most common wrong initial approach is fixing the frontend when the backend is the root cause
Step 2: Check for Stale Artifacts
Before any debugging, eliminate ghost bugs. Use the commands appropriate to the project stack — the pattern is "force rebuild + verify source matches running":
# Force rebuild (stack-specific)
# Examples:
# Go: go build ./...
# Node: rm -rf node_modules/.cache && npm run build
# Rust: cargo clean && cargo build
# Java/JVM: mvn clean compile
# Python: rm -rf __pycache__ dist build *.egg-info
# Verify dependencies haven't drifted
# Examples: go mod verify, npm ls, pip freeze, cargo tree
# Always check git state regardless of stack
git status --short
git log --oneline -3
# For production bugs, confirm deployed commit matches source
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.
- 2d ago First seen · 263 lines · 54 tokens per session scan C 34c0b46fa0fa
bugfix is a skill published in the GitHub repository JotJunior/cstk (22 stars, last pushed 3d ago), licensed MIT. It adds 54 tokens to every session and 2,553 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…