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/tomzx/agents/create-decisionnpx skills add tomzx/agents --skill create-decisiongit clone --depth 1 https://github.com/tomzx/agentsWhat 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 | $0.00022 | $0.00865 |
| Opus 5 | $0.00011 | $0.00432 |
| Sonnet 5 | $0.00004 | $0.00173 |
| Haiku 4.5 | $0.00002 | $0.00086 |
Grade A, and why
create-decision 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Decision
Records a decision made during implementation as a lightweight Architecture Decision Record (ADR). Captures the context, the decision, alternatives considered, trade-offs, and expected consequences so future contributors understand why the code is the way it is.
Prerequisites
- Apply the shared SDLC conventions in
skills/sdlc/references/shared.md. - A concrete decision that was made (or needs to be made) during implementation
- Enough context to explain the forces that shaped the decision
Steps
- Identify the decision: what question was answered or choice was made.
- Describe the context: what problem exists, what constraints apply, what prompted the decision.
- List the options that were considered (at least two, including the chosen one).
- State the decision clearly.
- Explain the trade-offs: what is gained and what is sacrificed.
- Describe the consequences: what changes as a result, what follow-up is expected.
- Save the document to
.sdlc/knowledge/decisions/(or the project's existing ADR directory if one exists) using the filename patternN-<slug>.mdwhereNis the next available number (counting existing files in that directory).
If this decision replaces an earlier one, run /supersede-decision <old> <new> afterwards to mark the prior ADR Superseded by [N] and record the reverse link. Do not hand-edit the older decision's status.
Output Format
Use the template at skills/sdlc/templates/knowledge/decision.md (copied to .sdlc/templates/knowledge/decision.md by /initialize-sdlc-directory; use the project's customized copy if present). Write the result to the artifact path named in the steps above.
Outcome
If $OUTCOME_YAML is set, emit verdict: approved there per skills/sdlc/references/shared.md once the record is written.
In the same emission, list the artifact under artifacts: (.sdlc/knowledge/decisions/N-<slug>.md, or the project's existing ADR directory when one is used).
Example Usage
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 · 76 lines · 22 tokens per session scan A 6e916f963380
create-decision is a skill published in the GitHub repository tomzx/agents (5 stars, last pushed 5d ago), licensed MIT. It adds 22 tokens to every session and 865 once invoked, about $0.0001 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…