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 nortonx/ai-tooling-free --skill generate-adrgit clone --depth 1 https://github.com/nortonx/ai-tooling-freeWrote 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/nortonx/ai-tooling-free/generate-adr)<a href="https://agentmods.dev/skills/nortonx/ai-tooling-free/generate-adr"><img src="https://agentmods.dev/badge/skills/nortonx/ai-tooling-free/generate-adr/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/nortonx/ai-tooling-free/generate-adr"><img src="https://agentmods.dev/badge/skills/nortonx/ai-tooling-free/generate-adr.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 | $0.00042 | $0.02078 |
| Opus 5.5 | $0.00017 | $0.00831 |
| Sonnet 5.5 | $0.00008 | $0.00416 |
| Haiku 4.5 | $0.00004 | $0.00208 |
Grade A, and why
generate-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 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.
How it starts
The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arguments
<decision title>
- Required. About 7 words describing the decision; the interview asks for it (Q1) but you can prefill via the arg.
- Examples:
/generate-adr Adopt Lefthook in place of Husky,/generate-adr Switch primary database to PostgreSQL
Copilot CLI note:
$ARGUMENTSdoes not substitute in skills; include the argument inline in your prompt.
Generate ADR: $ARGUMENTS
Create an Architecture Decision Record (ADR) in Michael Nygard's canonical 2011 format. ADRs are short, typically one page, and record a single architectural decision: its context, the decision itself, and its consequences. Detect the local ADR convention, interview the user one question at a time, draft an ADR that matches their team's existing style, and write it to disk only after explicit approval.
ADRs document decisions, not aspirations. The user provides the substance; this skill scaffolds structure and enforces brevity. Never pad empty sections with "TBD"; omit them entirely.
Step 1: Orient
Probe the working directory for an existing ADR location, in this order:
docs/adr/: Nygard recommendation, the most common convention.docs/architecture/decisions/: corporate / monorepo convention.doc/adr/: Linux-kernel-style.adr/at repo root: rare but valid.
- Exactly one exists: use it.
- Multiple exist: ask which to write to.
- None exist: propose
docs/adr/and tell the user you will bootstrap it at write-time, including an index README.
List existing ADRs by globbing <dir>/[0-9][0-9][0-9][0-9]-*.md. Parse the largest 4-digit prefix; the next ADR number is max + 1, zero-padded to 4 digits. Never gap-fill; gaps reflect deleted or rejected drafts and are part of the history.
If at least one ADR exists, read the highest-numbered one as a tone reference so the new ADR matches the team prose style (terseness, header casing, language).
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 Changed 33b6d704cc3d
- 1mo ago First seen · 151 lines · 42 tokens per session scan A 7eac7ece6719
generate-adr is a skill published in the GitHub repository nortonx/ai-tooling-free (1 stars, last pushed 18d ago), licensed MIT. It adds 42 tokens to every session and 2,078 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
api-security-patterns
Skill "api-security-patterns" from frank-luongt/faos-skills-marketplace, covering advanced api security patterns, when to use this skill, how it works, step 1: threat model the api surface and step 2: implement the authentication layer.
multi-agent-patterns
Skill "multi-agent-patterns" from frank-luongt/faos-skills-marketplace, covering multi-agent architecture patterns, when to activate, core concepts, detailed topics and why multi-agent architectures.
app-store-optimization
Skill "app-store-optimization" from frank-luongt/faos-skills-marketplace, covering app store optimization (aso), use this skill when, do not use this skill when, instructions and platform differences: apple vs. google.
campaign-analytics
Skill "campaign-analytics" from frank-luongt/faos-skills-marketplace, covering campaign analytics, use this skill when, do not use this skill when, instructions and multi-touch attribution models.
enterprise-search
Skill "enterprise-search" from frank-luongt/faos-skills-marketplace, covering enterprise search, use this skill when, do not use this skill when, instructions and search architecture patterns.
hr-operations
Skill "hr-operations" from frank-luongt/faos-skills-marketplace, covering hr operations, use this skill when, do not use this skill when, instructions and hiring pipeline dashboard.