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/moberghr/mtk-agent-toolkit/source-driven-developmentnpx skills add moberghr/mtk-agent-toolkit --skill source-driven-developmentgit clone --depth 1 https://github.com/moberghr/mtk-agent-toolkitWhat 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 | $0.00039 | $0.00496 |
| Opus 5 | $0.00019 | $0.00248 |
| Sonnet 5 | $0.00008 | $0.00099 |
| Haiku 4.5 | $0.00004 | $0.00050 |
Grade A, and why
source-driven-development 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 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.
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
Source-Driven Development
Overview
When framework behavior matters, memory is not enough. Verify unfamiliar APIs against authoritative sources and call out anything that remains unverified.
When To Use
- New or unfamiliar .NET, EF Core, AWS SDK, or package APIs
- Version-sensitive framework behavior
- Performance or security-sensitive framework usage
- Conflicting assumptions between repo patterns and tool memory
When NOT To Use
- Well-understood local code patterns already validated in the repo and unchanged by version differences
- Forward-looking "current best way" questions that need web research → use
research-context
Workflow
- Identify the uncertain API or behavior.
- Check whether the repo already demonstrates the same API safely.
- If not, consult authoritative documentation.
- Distinguish clearly between:
- verified from source
- inferred from local codebase pattern
- still uncertain
- Implement only after the uncertainty is resolved or explicitly surfaced.
Rules
- Do not present guessed framework behavior as fact.
- Prefer authoritative sources over memory.
- If the behavior cannot be verified, state that plainly.
Common Rationalizations
See .claude/skills/context-engineering/SKILL.md for the shared table. Source-driven-specific traps: "this API probably behaves like the last one I used" (similar names cause production bugs — verify the actual contract for this version), and "I'll fix it if it breaks" (source checks are cheaper than post-failure recovery, especially for transaction or security behavior).
Red Flags
- New framework usage with no evidence behind it
- Version-sensitive assumptions stated as certainty
- Security or transaction behavior guessed from memory
Verification
- Uncertain APIs were identified
- Authoritative sources or proven repo patterns were used
- Remaining uncertainty, if any, was surfaced explicitly
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 · 65 lines · 39 tokens per session scan A b6583608265a
source-driven-development is a skill published in the GitHub repository moberghr/mtk-agent-toolkit (6 stars, last pushed 8d ago), licensed MIT. It adds 39 tokens to every session and 496 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 2026-08-31.
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…