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/davidmatousek/agentic-oriented-development-kit/aod-bugfixnpx skills add davidmatousek/agentic-oriented-development-kit --skill aod-bugfixgit clone --depth 1 https://github.com/davidmatousek/agentic-oriented-development-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 | $0.00083 | $0.05034 |
| Opus 5 | $0.00042 | $0.02517 |
| Sonnet 5 | $0.00017 | $0.01007 |
| Haiku 4.5 | $0.00008 | $0.00503 |
Grade A, and why
~aod-bugfix 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.
How it starts
The opening of the file, as written. The whole thing — 381 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/aod.bugfix — One-Shot Bug Fix Command
Pre-Run Safety
Advisory (non-blocking): Before proceeding, consider stashing or committing any in-progress work (
git stashorgit commit). If Phase 3 fails mid-execution, partial edits can be reverted cleanly from a known-good state.
[Phase 0] Acknowledging input...
Phase 0: Input Acknowledgment & Context Summary
Detect the input mode based on what the user provided:
If pasted content (error message, stack trace, logs, or failing test output):
First, check whether an error or symptom is identifiable in the pasted content:
- If no error message or symptom is visible (e.g., the paste contains only code, config, or prose with no failure signal): stop and ask specifically — "I don't see an error message or failure symptom in what you pasted. Can you share the actual error, exception, or unexpected behavior you're seeing?" Do not proceed to Phase 0b until a failure signal is present.
If an error or symptom is present, proceed with parsing:
- Multi-error input: If multiple errors or exceptions appear, identify the PRIMARY failure — the first error in chronological order or the root-level exception (not cascading/downstream errors). Scope all acknowledgment and analysis to the primary failure only. In the context summary output, briefly note how many secondary errors were present and that they are considered downstream (e.g., "Note: 2 additional errors detected — treated as downstream of primary failure"). Do not analyze secondary errors separately.
- Stack trace summarization: When a multiline stack trace is present, do not pass it through raw. Summarize it in one line, e.g.: "Received: TypeError in src/foo.ts, 12-frame stack trace starting at bar()". Use the actual error type, file, frame count, and top frame from the trace.
- List any additional files or modules named in the output (beyond those in the summary line)
After parsing, output a 2-3 line context summary before continuing, using this format:
Input received: <error type> in <file/module>
Primary failure: <one-sentence description of the root error>
Scope: <files/components involved, or "unknown — proceeding to KB check">
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 · 381 lines · 83 tokens per session scan A c2f927a657cf
~aod-bugfix is a skill published in the GitHub repository davidmatousek/agentic-oriented-development-kit (22 stars, last pushed 2mo ago), licensed MIT. It adds 83 tokens to every session and 5,034 once invoked, about $0.0004 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.
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.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
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.