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/fledgeling-co/fledgeling-plugins/geminifynpx skills add fledgeling-co/fledgeling-plugins --skill geminifygit clone --depth 1 https://github.com/fledgeling-co/fledgeling-pluginsWrote 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/fledgeling-co/fledgeling-plugins/geminify)<a href="https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/geminify"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/geminify.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 | $0.00337 | $0.05259 |
| Opus 5 | $0.00169 | $0.02629 |
| Sonnet 5 | $0.00067 | $0.01052 |
| Haiku 4.5 | $0.00034 | $0.00526 |
Grade A, and why
geminify 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 today.
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 — 377 lines — stays where its author put it; the contents beside it link to each section on GitHub.
geminify
A skill is a prompt. Prompts are tuned — usually silently, usually to whichever model the author was running. Most of the skills in this ecosystem were written against Claude's failure modes, and several of their most deliberate decisions are removals: guidance stripped out because Claude over-does that thing when told to.
On Gemini those removals leave a vacuum, and the vacuum fills with something plausible. This skill writes the layer that fills it deliberately instead.
The output is one file, gemini.md, beside the target's SKILL.md, plus a
conditional pointer at the top of the SKILL.md that other models skip. Not a
rewrite of the skill: the canon transfers. What does not transfer is the
assumption that a rule stated in prose gets executed.
Running as a Gemini model? Read gemini.md in this directory first, then follow this file with the overrides it names. It gives the scan's rows, the fired modules and the vendor quotes a count each, turns 150–250 lines and the batch's --bump none into a bound ledger read back off the written file, and adds the prerequisite-receipt checks verify_quotes.py cannot make. Other models skip it.
Two modes, and which one you are in
| You were asked to | Mode | Runs |
|---|---|---|
geminify a named skill: geminify design-craft, "write a gemini.md for X" |
A | the six steps under Mode A |
calibrate the session you are running in: /geminify with no target, or a hook told you this session is served by Gemini |
B | the four steps under Mode B |
Mode B exists because it was already happening without a procedure. Between 18
August and 1 September 2026 six sessions invoked this skill; three were runners
calibrating themselves rather than authoring anything, and one of those loaded five
skills and read zero gemini.md files while running on Gemini. Nothing noticed,
because nothing counted.
A target named in the invocation means Mode A; no target means Mode B. When the invocation names a target and the session is on Gemini, run Mode B first — four tool calls, and it changes how Mode A's judgement calls go.
What ships with it
9 files 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.
- today Changed · +95 lines · +122 tokens per session 3b6062442e8f
- 4d ago First seen · 282 lines · 215 tokens per session scan A bf3da17288f2
geminify is a skill published in the GitHub repository fledgeling-co/fledgeling-plugins (2 stars, last pushed today), licensed MIT. It adds 337 tokens to every session and 5,259 once invoked, about $0.0017 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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…