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 fledgeling-co/fledgeling-plugins --skill email-digestgit 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/email-digest)<a href="https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/email-digest"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/email-digest.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 5.1 | $0.00217 | $0.04875 |
| Opus 5 | $0.00109 | $0.02438 |
| Sonnet 5 | $0.00043 | $0.00975 |
| Haiku 4.5 | $0.00022 | $0.00487 |
Grade A, and why
email-digest 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 — 355 lines — stays where its author put it; the contents beside it link to each section on GitHub.
email-digest
A digest that goes out with twenty-four items and comes back described as unreadable has a real defect, and it is almost never the one people name. Cutting the list is the intuitive fix and the evidence goes the other way: MailerLite's 317,000 campaigns and 2.9 billion emails put the 21-or-more-links bucket at the highest click-to-open rate in the dataset, and the choice-overload meta-analysis pools to a mean effect size of virtually zero.
The defect is undifferentiated scan cost per item. Fifty-one seconds of attention, every item costing the same fixation to evaluate, and nothing in the visual field saying where to stop. Tiering fixes that. Truncation does not; it just removes content somebody asked for.
So this skill does not cap the item count, and scripts/lint_email.py asserts
the absence of a cap as a rule, because that cap re-enters the code every time
somebody reasons from first principles instead of reading the evidence.
Full provenance for every rule: references/evidence.md. Read it when you need
to justify or change a rule, not on every run.
Using Gemini? Read gemini.md for this skill's task-specific calibration and artifact checks. Its older runs do not establish Gemini 3.8 capability limits: preserve the user's selected implementation lane, and apply a model-specific route only when the current model or an observed failure supports it.
What this produces
An HTML part, a plain-text part, and a gate report. It does not send. Whatever already sends (an ESP, a cron route, a queue) keeps that job.
Step 1 — Find the source and the brand
Discover rather than assume; a hard-coded map goes stale silently and only ever fits one project.
- The items. A database collection, a JSON file, a changelog, a directory of markdown, an API. Ask if it is genuinely unclear; do not invent a schema.
- The palette and marks. Look for design tokens (
tokens.css,theme.ts, a Tailwind config) and take the real values. Email clients do not resolve CSS custom properties, so tokens must be flattened to literals at build time. - Brand assets. Note the format. Gmail strips
<svg>from the DOM entirely, so a vector mark has to be rasterised before it can appear. - Where images are served from. Every asset needs an absolute URL on a host the recipient can reach. A path that works on the site does not work in mail.
What ships with it
6 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 541db575409d
- 8d ago First seen · 355 lines · 217 tokens per session scan A 3b0c152ee093
email-digest is a skill published in the GitHub repository fledgeling-co/fledgeling-plugins (2 stars, last pushed yesterday), licensed MIT. It adds 217 tokens to every session and 4,875 once invoked, about $0.0011 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…
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…
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…