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/nullhack/temple8/record-decisionnpx skills add nullhack/temple8 --skill record-decisiongit clone --depth 1 https://github.com/nullhack/temple8What 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 | $0.00028 | $0.00483 |
| Opus 5 | $0.00014 | $0.00242 |
| Sonnet 5 | $0.00006 | $0.00097 |
| Haiku 4.5 | $0.00003 | $0.00048 |
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 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
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.templatetodocs/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 logwith 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, andConsequencesto the current decision — and append aChange logrow (<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
Traceabilityresolves to a real artefact before finishing.
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 · 15 lines · 28 tokens per session scan A 43b009a8a91b
record-decision is a skill published in the GitHub repository nullhack/temple8 (11 stars, last pushed 27d ago), licensed MIT. It adds 28 tokens to every session and 483 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 2026-08-30.
Other skills, from other repositories
load-github-action-thread
Download retained Codex GitHub Action thread artifacts and load their rollout history into the local Codex app. Use when asked to open, load, import, resume, or inspect a Codex automation thread from a GitHub Actions run or a related GitHub issue or pull request.
test-generator
Generate pytest test cases for Python functions and classes.
python-binance
Help developers use the python-binance library for trading on Binance. Use when code imports binance, references Client/AsyncClient, or asks about Binance API trading, market data, websockets, or account management.
itx:execute
Execute the plan for an issue (parent or subtask).
clawctl
Know the clawctl CLI and manage your Clawrium fleet (hosts, agents, providers, channels, integrations, skills, secrets).
create-playwright
Record a browser-session demo (MP4) using Playwright via a replay-first compile pipeline. A YAML spec drives the driver script, the recording, and the ElevenLabs voiceover — mirrors create-vhs for browser flows.