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/leifericf/agentic-sdk/record-decisionnpx skills add leifericf/agentic-sdk --skill record-decisiongit clone --depth 1 https://github.com/leifericf/agentic-sdkWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/leifericf/agentic-sdk/record-decision)<a href="https://agentmods.dev/skills/leifericf/agentic-sdk/record-decision"><img src="https://agentmods.dev/badge/skills/leifericf/agentic-sdk/record-decision.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00021 | $0.00571 |
| Opus 5 | $0.00010 | $0.00285 |
| Sonnet 5 | $0.00004 | $0.00114 |
| Haiku 4.5 | $0.00002 | $0.00057 |
Grade A, and why
record-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 4d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
record-decision
Architecture decisions are ADRs, written when the decision happens, not
reconstructed later. Store and format come from the descriptor (:adr;
default docs/adr/, nygard). Fields and voice are fixed in the "Decision
records" section of references/prose-style.md.
Procedure
-
Decide whether to record. Record when a discussion ends in "do X, not Y" and X constrains future work, or when your work settles a real choice where the rejected option was reasonable, or when you reject a review finding as deliberate and no record covers it. Do not record choices with one reasonable option, reversible implementation details, or anything an existing ADR covers (supersede it instead if the answer changed).
-
Next number. Read
docs/adr/README.md(create it as[]if missing), take the highest number, add one, two digits. The first ADR is01. -
Write
docs/adr/NN-slug.md:# ADR NN: <the decision, readable in the index> Date: YYYY-MM-DD ## Context ## Decision ## Consequences ## AlternativesOne screenful (about 40 to 60 lines). Context is neutral, no foreshadowing. Decision is one paragraph, present tense. Consequences include the costs. Alternatives get their real strengths before the rejection. Superseding: say "Supersedes ADR NN" in the Decision; never edit the old record.
-
Add the one-line row to the
docs/adr/README.mdindex. -
Route the rule too. If the decision changes how code is written (a banned idiom, a new constraint), add the rule to the right reference or skill. The ADR holds the why; the reference holds the how. Cross-cite.
-
Commit.
Docs: Record ADR NN, <short title>(or fold into the change's commit series when recorded mid-change).
Boundaries
Owns the why of an architecture decision. The enforced how lives in a
reference or lint rule, routed in step 5. Bulk promotion of captured
guidance is incorporate-feedback. Does not record reversible
implementation details or one-option choices.
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.
- 4d ago First seen · 62 lines · 21 tokens per session scan A f7f0dd81b9bb
record-decision is a skill published in the GitHub repository leifericf/agentic-sdk (5 stars, last pushed 2d ago), licensed MIT. It adds 21 tokens to every session and 571 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…