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-plangit 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-plan)<a href="https://agentmods.dev/skills/kgiwojno/g-sdd/g-plan"><img src="https://agentmods.dev/badge/skills/kgiwojno/g-sdd/g-plan/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-plan"><img src="https://agentmods.dev/badge/skills/kgiwojno/g-sdd/g-plan.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 | $0.00043 | $0.04885 |
| Opus 5 | $0.00022 | $0.02442 |
| Sonnet 5 | $0.00009 | $0.00977 |
| Haiku 4.5 | $0.00004 | $0.00488 |
Grade B, and why
g-plan scanned grade B with 1 finding 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 12d 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.
Asks the agent to reveal its instructionsmediumSystem prompt leakage
Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.
back to the same yes/no/show prompt. How it starts
The opening of the file, as written. The whole thing — 562 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Behavior
1. Check prerequisites
Check if docs/features/ contains any feature directories.
If not, stop: "No feature found. Please run /g-prd first."
If there are multiple features, list them and ask which one to plan for. If there's only one, use it.
Check if the selected feature has a PRD.md. If not, stop:
"No PRD found in docs/features/[name]/. Please run /g-prd first."
Read the PRD as context — particularly the Implementation
Decisions and Testing Decisions sections.
Also read CONTEXT.md at the repo root if it exists. The
## Language entries are the project's canonical
vocabulary — reuse those terms (don't redefine them) and
treat any ## Flagged ambiguities resolutions as
load-bearing decisions when shaping the plan. If CONTEXT.md
is absent (greenfield or pre-retrofit project), proceed
without it; the step-4 interview may populate it.
Run this read literally on every invocation. Do not skip the read on observation that the file looks empty or header-only — the explicit read IS the spec compliance signal.
Also read any existing ADRs in docs/adr/. These represent
prior architectural decisions that may apply to this feature.
Verify-and-switch to the feature branch. Before any file
write, ensure the working tree is on the feature branch
{feature-name}. The switch is silent — invoking the stage
implies the operator's intent.
Run this block literally. Do not paraphrase, shortcut on observation ("I can see we're already on the feature branch"), or skip when the current branch appears correct. The explicit run IS the spec compliance signal.
expected="{feature-name}" # from selected feature directory
current=$(git rev-parse --abbrev-ref HEAD)
if [ "$current" = "$expected" ]; then
: # already on it
elif git show-ref --verify --quiet "refs/heads/$expected"; then
git checkout "$expected"
else
echo "feature branch '$expected' missing — run /g-prd to create it"
exit 1
fi
If the feature branch doesn't exist, STOP without modifying any file.
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.
- 12d ago First seen · 562 lines · 43 tokens per session scan B 1b8de9b86cc9
g-plan is a skill published in the GitHub repository kgiwojno/g-sdd (6 stars, last pushed 2mo ago), licensed MIT. It adds 43 tokens to every session and 4,885 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). 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…