What is record-decision?

A skill for writing or amending an Architecture Decision Record, a document that captures an important choice and its trade-offs. It first checks whether the decision affects enough of the system to deserve a record.

Use it to document cross-cutting architectural decisions with multiple viable options, including why alternatives were rejected and how negative consequences will be managed.

It prevents minor implementation choices from becoming unnecessary documentation. For significant decisions, it creates a consistent record of context, alternatives, consequences, and links to supporting evidence.

record-decision — Skill for OpenCode by nullhack/temple8

Install

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.

Any agent

npx skills add nullhack/temple8 --skill record-decision

Clone the repo

git clone --depth 1 https://github.com/nullhack/temple8

Made for: OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/nullhack/temple8/record-decision/github.svg)](https://agentmods.dev/skills/nullhack/temple8/record-decision)

Your own site

<a href="https://agentmods.dev/skills/nullhack/temple8/record-decision"><img src="https://agentmods.dev/badge/skills/nullhack/temple8/record-decision/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/nullhack/temple8/record-decision"><img src="https://agentmods.dev/badge/skills/nullhack/temple8/record-decision.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 483 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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 5.1	$0.00028	$0.00483
Opus 5.5	$0.00011	$0.00193
Sonnet 5.5	$0.00006	$0.00097
Haiku 4.5	$0.00003	$0.00048

Measured 1mo ago against content hash 43b009a8a91b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 1mo 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.

.opencode/skills/record-decision/SKILL.md · 15 lines

What it actually says

Record Decision

Confirm the decision is ADR-worthy before authoring: it has genuine trade-offs between multiple viable alternatives and cross-cutting impact (reversing it would ripple across contracts). IF it has one obvious choice or only local impact THEN it is BAU — do not record it; stop here.
Copy .templates/docs/decisions/YYYY-MM-DD-<kebab-title>.md.template to docs/decisions/<today>-<slug>.md, replacing the date placeholder with today's ISO date and the slug with a short kebab title for the decision.
Fill the sections from the decision itself, not from memory of the alternatives: Context (the forces — link the interview, glossary, existing ADRs, cassettes, and the contract set; do not restate them), Decision (one imperative sentence), Alternatives considered (each alternative + why it was rejected), Consequences (+ / − / neutral, with mitigations for the negatives). Apply the prose bar per [[writing/ai-language-markers]] — scrub AI markers (delve, tapestry, plays a crucial role, rather than); the ADR's authority comes from the decision's forces, not formal-sounding prose.
In Traceability, link the artefacts the decision touches — tests, source .pyi, migrations, cassettes, glossary terms, related ADRs — by path. Points only; never restate the artefact's content (tests are the source of truth).
Seed the Change log with one row: <today> | Created | <one-line reason>.
IF the decision supersedes an existing ADR THEN edit that ADR in place — amend its Status, Decision, Alternatives considered, and Consequences to the current decision — and append a Change log row (<today> | Amended | <what changed and why>). Do not create a new file; the body always reflects the current decision and the log carries the history.
Verify every path in Traceability resolves to a real artefact before finishing.

Changes

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.

1mo ago First seen · 15 lines · 28 tokens per session scan A 43b009a8a91b

Subscribe to this mod's changes

record-decision is a skill published in the GitHub repository nullhack/temple8 (11 stars, last pushed 29d ago), licensed MIT. It adds 28 tokens to every session and 483 once invoked, about $0.0001 per session on Opus 5.5. 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.

Planning Python project-template pytest python-project-template python3 uv

test-generator

Generate pytest test cases for Python functions and classes.

vstorm-co/pydantic-deepagents · 12 tokens

python

Use when the task is Python itself, in any framework or none: PEP 695 generics, mypy --strict typing, dataclass/Protocol/TypedDict/Enum choices, asyncio.TaskGroup, stdlib idioms, src/ layout + pyproject.toml with uv, ruff+mypy+pytest gate. NOT a FastAPI/ASGI service (that is fastapi), NOT a deep pytest suite (that is…

ericrisco/rsc-harness · 94 tokens

record-decision

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Record Decision

What this file has done since we first saw it

Other skills, from other repositories

test-generator

python

clawrium-release-announcements

blog-author

release-watcher

daily-digest