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 skills add arch3rPro/dsh-skills --skill decision-recordsgit clone --depth 1 https://github.com/arch3rPro/dsh-skillsWrote 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/arch3rpro/dsh-skills/decision-records)<a href="https://agentmods.dev/skills/arch3rpro/dsh-skills/decision-records"><img src="https://agentmods.dev/badge/skills/arch3rpro/dsh-skills/decision-records/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.
<a href="https://agentmods.dev/skills/arch3rpro/dsh-skills/decision-records"><img src="https://agentmods.dev/badge/skills/arch3rpro/dsh-skills/decision-records.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00090 | $0.01025 |
| Opus 5 | $0.00045 | $0.00513 |
| Sonnet 5 | $0.00018 | $0.00205 |
| Haiku 4.5 | $0.00009 | $0.00103 |
Grade A, and why
decision-records 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 10d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decision Records
An Architecture Decision Record (ADR) captures the why and what we gave up behind a design decision — the parts code and docs cannot carry. This skill covers where records live, when to write one, and the in-file structure. It applies to any project that wants its rationale to outlive the change.
The defining constraint: an ADR records a decision — the alternatives it beat and the consequences it accepted — not a transcript of how the decision was reached. A decision without its rejected alternatives invites re-litigation.
Layout and lifecycle
Every record has two axes:
- Lifecycle — its status, which changes over time:
- proposed — not yet built (or only partly); the plan and open questions live here.
- accepted / implemented — the decision shipped; the file describes shipped reality in the present tense and is kept current with what actually shipped (facts — paths, names, structure — not the decision itself).
- rejected — considered and declined; keep it only while its rationale prevents a tempting, meaningful mistake.
- Class — the kind of decision (feature, bug-fix, simplification, architecture, process, testing). Pick the class folder that matches.
A record moves between lifecycle folders as its status changes; the move updates the status line and the body's form in the same change.
When to write one
Write (or update) an ADR when a change is non-trivial: it alters behavior, architecture, a contract shared across files or modules, process or tooling, testing strategy, an on-disk/wire/config format, or another decision a maintainer may reasonably revisit. A purely mechanical or local edit with no behavior/contract/structure change is exempt.
Never edit a record into a different decision. Supersede it with a new one and keep both cross-linked, unless the old one is fully superseded and can be consolidated into the new owner.
The in-file structure
Every record opens with the decision's problem — written to stand without the solution. What follows depends on the lifecycle:
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 61 lines · 90 tokens per session scan A feae7f05a749
decision-records is a skill published in the GitHub repository arch3rPro/dsh-skills (4 stars, last pushed 23d ago), licensed MIT. It adds 90 tokens to every session and 1,025 once invoked, about $0.0005 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
tastemaker
Generate genuinely beautiful, on-brand UI instead of generic "AI slop" — use whenever the user asks to build, design, style, or improve a UI, landing page, dashboard, app screen, or component, whenever a PRD/spec needs a design pass before implementation, whenever the user pastes reference images/Pinterest/Dribbble…
johnny-suede-design
Suede Labs AI full-stack surface builder that runs design, copy, and visual QA as one pass: landing pages, brand surfaces, product UI, dashboards, campaigns, launch pages, and reference-to-target restyles (suedify). Use when a build needs layout and words together, when a redesign or launch surface has to ship end to…
suede-code-review
Suede Labs AI findings-only code review with full context: changed files, callers, contracts, and deploy surface. Covers TypeScript, React, Next.js, database, Swift/iOS, OWASP, accessibility, SEO, observability, commit hygiene, and deploy risk, ranked P0-P3 with file:line evidence and a fix path. Use when asked to…
suede-social
Suede-owned organic social strategy and content discipline. Use when planning platform mix, posts, threads, cross-platform calendars, repurposing, listening, engagement, or cadence for a founder or brand account. NOT FOR: Instagram-specific account audits, Reels, carousels, Stories, or daily Instagram loops (use…
voice-preserving-line-edit
Context-aware line edit that strips generic AI writing patterns without flattening the author's voice, plus a findings-only audit mode that names issues instead of rewriting. Applies contextual rules rather than blanket bans on adverbs, passive voice, and punctuation, and locks facts, numbers, quotes, code, links, and…
suede-clip-to-guide
Suede-owned short-to-long content funnel blueprint. Use when turning a video, clip, interview moment, talk excerpt, screen recording, or transcript into a repeatable package that bridges attention to an X Article, LinkedIn article, newsletter, blog guide, or playbook, or when third-party footage needs a rights route…