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 kgiwojno/g-sdd --skill g-adrgit clone --depth 1 https://github.com/kgiwojno/g-sddWrote 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/kgiwojno/g-sdd/g-adr)<a href="https://agentmods.dev/skills/kgiwojno/g-sdd/g-adr"><img src="https://agentmods.dev/badge/skills/kgiwojno/g-sdd/g-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/kgiwojno/g-sdd/g-adr"><img src="https://agentmods.dev/badge/skills/kgiwojno/g-sdd/g-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 | $0.00049 | $0.01677 |
| Opus 5 | $0.00024 | $0.00839 |
| Sonnet 5 | $0.00010 | $0.00335 |
| Haiku 4.5 | $0.00005 | $0.00168 |
Grade A, and why
g-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 11d 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 — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Behavior
This skill operates in two modes:
- Standalone audit — invoked directly via
/g-adr - Post-implementation — invoked by
/g-implementafter all slices complete, scoped to the current feature
Both modes spawn the g-architect named subagent to do the
gap detection and draft generation. This skill owns the human-
in-the-loop flow that turns proposed drafts into accepted (or
rejected) ADRs on disk.
Auto-numbering
The architect numbers monotonically: next ADR is
highest existing + 1 regardless of any ADR's status. Rejected
drafts retain their number; numbers are never reused. The skill
verifies this on read by listing docs/adr/ after the architect
returns and confirming no collisions.
Standalone Audit Mode
Invoked when the user runs /g-adr directly.
1. Check prerequisites
Check if docs/adr/ exists. If not, suggest running /g-setup
first.
2. Spawn g-architect (audit mode)
/g-adr runs from the repo root, not a worktree. cwd is
already the project root, which is what the architect needs.
Run the cd line literally for parity with /g-implement and
/g-fix; it is a no-op when the orchestrator is already at the
repo root, but the discipline is uniform across spawn
callsites.
cd "$repo_root"
Task tool invocation:
subagent_type: g-architect
description: Architect — audit
prompt: <<EOF
<!-- g-sdd:work-unit-type=feature-level -->
<!-- g-sdd:agent-role=architect -->
<!-- g-sdd:feature-name={feature-name} -->
You are the g-architect subagent.
## spec
Mode: audit. Sweep the project for undocumented
architectural decisions and stale ADRs. Draft new ADRs to
disk with Status: Proposed. Return stale-ADR update
proposals in your response (do NOT modify existing files).
Apply the three-criteria filter from
`docs/templates/adr.md` `## When to create an ADR`
section. Propose Drafts only for decisions where all
three criteria hold (hard-to-reverse / surprising /
real trade-off). Decisions failing the filter are
recorded in observation, not as ADR proposals. Audit
mode has no Draft pre-stage — filter-passing decisions
are written directly as `Status: Proposed`.
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.
- 11d ago First seen · 231 lines · 49 tokens per session scan A 23cb7832f0e8
g-adr is a skill published in the GitHub repository kgiwojno/g-sdd (6 stars, last pushed 2mo ago), licensed MIT. It adds 49 tokens to every session and 1,677 once invoked, about $0.0002 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…