A digest command that summarizes a branch, pull request, code diff, or design document into a structured report. A pull request is a proposed set of code changes for review.

Creating concise terminal summaries or exporting fuller Markdown or HTML reports tailored to audiences such as developers, managers, or security reviewers.

It helps reviewers and stakeholders understand what changed, why it changed, and which files and concepts are involved without reading everything first.

digest — Command by shdennlin

Install

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.

agentmods

npx agentmods add commands/shdennlin/agent-plugins/digest

Clone the repo

git clone --depth 1 https://github.com/shdennlin/agent-plugins

Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,520 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00023	$0.01520
Opus 5	$0.00012	$0.00760
Sonnet 5	$0.00005	$0.00304
Haiku 4.5	$0.00002	$0.00152

Measured yesterday against content hash 34a03a05b672, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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.

plugins/digest/commands/digest.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Digest Command

Produce a structured summary of AI-generated changes so developers, reviewers, and stakeholders can quickly understand what changed and why.

Arguments

Parse the following from $ARGUMENTS:

[target] — A branch name, PR number (#42), file path, or omit for current branch
-f, --for <audience> — Tailor material and language for an audience. Free-form string (e.g. manager, pm, designer, non-technical, "security auditor"). Default: developer/reviewer
-e, --export [md|html] — Write a full-depth report file. md = markdown with Mermaid diagrams (default when no value given); html = self-contained HTML explainer
--help or -h — Show usage information and exit

Output rule: terminal output is always the concise card; export output is always the full-depth report. The audience flag calibrates both.

Instructions

Step 1: Parse Arguments

From $ARGUMENTS, extract:

help: if --help or -h is present, show usage info below and stop. Do NOT delegate to the agent.
audience: if -f or --for is present, the next token is the audience string, taken verbatim — do NOT validate against a list. Default: developer.
export format: if -e or --export is present:
- If the very next token is exactly md or html, that token is the format and is consumed.
- Otherwise the format is md (bare export) and the token is NOT consumed — it stays positional. Example: -e feat/auth means "export md" with target feat/auth.
- If the flag is absent, export format is none.
target: the remaining positional argument (branch, #<number>, file path, or empty)

Removed flags — print a migration hint, do NOT error:

-r / --report present → print Note: -r was removed in 2.0 — full reports now live in exports. Use -e md or -e html. Strip the flag and continue.
-s / --simple present → print Note: -s was removed in 2.0 — use -f non-technical (or any audience). Set audience to non-technical and continue.

Read the full file on GitHub · 150 lines

Changes

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 · 150 lines · 23 tokens per session scan A 34a03a05b672

Subscribe to this mod's changes

digest is a command published in the GitHub repository shdennlin/agent-plugins (2 stars, last pushed 8d ago), licensed MIT. It adds 23 tokens to every session and 1,520 once invoked, about $0.0001 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.

Code review Git and workflow Security

digest

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Digest Command

Arguments

Instructions

Step 1: Parse Arguments

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

analyze

converge

implement