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/helderberto/agent-skills/create-adrnpx skills add helderberto/agent-skills --skill create-adrgit clone --depth 1 https://github.com/helderberto/agent-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/helderberto/agent-skills/create-adr)<a href="https://agentmods.dev/skills/helderberto/agent-skills/create-adr"><img src="https://agentmods.dev/badge/skills/helderberto/agent-skills/create-adr.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 | $0.00077 | $0.01032 |
| Opus 5 | $0.00039 | $0.00516 |
| Sonnet 5 | $0.00015 | $0.00206 |
| Haiku 4.5 | $0.00008 | $0.00103 |
Grade A, and why
create-adr 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create ADR
Capture architectural decisions as durable, minimal records future-you (and future-Claude) can read instead of guessing from code.
Gate — write an ADR only if all three are true
- Hard to reverse — changing your mind later costs meaningful effort (migration, rewrite, vendor lock-in).
- Surprising without context — a future reader will look at the code and wonder "why did they do it this way?"
- Real trade-off — there were genuine alternatives, and you picked one for specific reasons.
If any criterion is missing, say so and skip the ADR. Easy-to-reverse decisions get reversed; obvious decisions don't need recording; non-decisions ("we did the only thing that worked") aren't ADRs.
Cheap rejections prevent ADR sprawl. When in doubt, refuse and ask the user to confirm the decision really meets all three.
What qualifies
- Architectural shape — "monorepo," "event-sourced write model + projected read model"
- Integration patterns between modules/contexts — "Ordering and Billing communicate via events, not synchronous HTTP"
- Technology choices with lock-in — database, message bus, auth provider, deployment target. Not every library — only ones that take a quarter to swap.
- Boundary and ownership decisions — "Customer data is owned by Customer; other contexts reference by ID."
- Deliberate deviations from the obvious path — "manual SQL instead of an ORM because X." Stops the next engineer "fixing" a deliberate choice.
- Constraints not visible in code — "no AWS due to compliance," "must respond <200ms due to partner SLA."
- Rejected alternatives when the rejection is non-obvious — considered GraphQL, picked REST for subtle reasons. Otherwise someone re-suggests it in six months.
Workflow
1. Verify the gate
Restate the decision in one sentence. Check it against all three criteria explicitly. If it fails, tell the user which criterion failed and stop.
2. Locate docs/adr/
- If
docs/adr/exists, scan for the highestNNNN-*.mdfilename and increment. - If it doesn't exist, create it lazily — only now that there's something to write.
- Numbering: zero-padded 4 digits (
0001,0002, …).
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 · 91 lines · 77 tokens per session scan A ce29c4851372
create-adr is a skill published in the GitHub repository helderberto/agent-skills (14 stars, last pushed 2d ago), licensed MIT. It adds 77 tokens to every session and 1,032 once invoked, about $0.0004 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
release
Curate a release for the Claude Manager extension — analyze git commits since last tag, categorize them, generate a release notes markdown file in docs/releases/, decide the correct version bump, update CHANGELOG.md, and push a commit that triggers the CI/CD workflow to publish.
hcom-agent-messaging
Multi-agent communication for AI coding tools. Agents message, watch, and spawn each other across terminals. Use when setting up hcom, troubleshooting delivery, or writing multi-agent scripts.
env-scanner
Scan and audit Gemini CLI, Claude Code, Antigravity, Continue, Windsurf, JetBrains AI, and OpenCode environments. Discovers configurations, audits memory tiers, detects skill extraction state, analyzes behavioral tool chains, checks policy governance (v0.40+), and suggests reusable skills with evidence gating.…
scan
Scan your AI coding tool ecosystem — Gemini CLI, Claude Code, Antigravity (Desktop, CLI, IDE), Continue, Windsurf, JetBrains AI, OpenCode. Produces a maturity score, advisory recommendations, and optionally generates reusable SKILL.md files from your conversation patterns. Use when the user asks to audit their…
make-decision
AI-powered decision-making framework: 10+ methodologies, cognitive bias detection, strategic planning, career & business decisions. Use when user says "decide", "choose", "compare", "which one", "should I", "weigh options", "trade-off", "pros and cons", "help me pick", "evaluate", "select", "prioritize", "nên chọn cái…
problem-solving-pro
Systematic problem-solving toolkit: root cause analysis, hypothesis testing, debugging strategies, critical thinking frameworks. Use when user says "solve", "analyze", "diagnose", "debug", "figure out", "what's wrong", "root cause", "why is this happening", "I'm stuck", "break down", "decompose", "structure", "tại sao…