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/shdennlin/agent-plugins/digestnpx skills add shdennlin/agent-plugins --skill digestgit clone --depth 1 https://github.com/shdennlin/agent-pluginsWhat 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 | $0.00124 | $0.00619 |
| Opus 5 | $0.00062 | $0.00309 |
| Sonnet 5 | $0.00025 | $0.00124 |
| Haiku 4.5 | $0.00012 | $0.00062 |
Grade A, and why
digest: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 yesterday.
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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Digest
Summarize AI-generated changes into structured digests that developers, reviewers, and stakeholders can quickly understand.
Usage
$digest # current branch vs main
$digest feat/new-auth # specific branch
$digest #42 # PR number
$digest docs/plans/auth.md # design doc
$digest -f manager # impact/risk/decision framing
$digest -f non-technical # plain language
$digest -e md # full markdown report with Mermaid
$digest -e html # self-contained HTML explainer
$digest feat/auth -e html -f pm # combine target, export, audience
Options
| Flag | Description |
|---|---|
-f, --for <audience> |
Tailor material and language for an audience — free-form string (manager, pm, designer, non-technical, ...). Default: developer/reviewer |
-e, --export [md|html] |
Write a full-depth report file. md = markdown with Mermaid (default when no value); html = self-contained HTML explainer |
Output rule: terminal output is always the concise card (~1 min); export output is always the full-depth report. Removed flags: -r (use -e md/-e html), -s (use -f non-technical).
Process
- Detect input type (PR, branch, design doc, or current branch)
- Dispatch the digest agent using the prompt template in
digest-agent.md(in this skill directory) - Analyze changes and produce the audience-calibrated card, plus the full-depth report file if exporting
- Report the card back to the user (and the written file path when exporting)
Agent Dispatch
Use the companion digest-agent.md in this directory as the agent prompt. Provide it with:
- Input type and target
- Audience (free-form string, default
developer) - Export format (
none,md, orhtml) - For html export: the HTML template at
../../templates/html-explainer.mdrelative to this directory
The agent uses $PROJECT_ROOT (set by the init hook) or falls back to git rev-parse --show-toplevel.
What ships with it
1 file 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.
- yesterday First seen · 49 lines · 124 tokens per session scan A 9e10e62b2ede
digest:digest is a skill published in the GitHub repository shdennlin/agent-plugins (2 stars, last pushed 8d ago), licensed MIT. It adds 124 tokens to every session and 619 once invoked, about $0.0006 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.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
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…
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…
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…