tldr

tldr is a command for coding agents from pehcastro/harness. It costs 29 tokens per session (537 once invoked), scanned A, original, MIT.

A command that condenses a previous conversation into a short summary. It can summarize the last reply, the whole session, the last few replies, or a named subject.

In plain words
What is it for?
Use it with /tldr, /tldr session, /tldr last N, or another subject to produce a compact summary.
Why use it?
It removes background detail when someone needs the decision, open questions, risks, or key numbers quickly. It is intended for readers who already saw the original discussion.

Command

Part of the brevity plugin — 1 skill, 1 command, 1 agent, 2 hooks shipped together

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/pehcastro/harness/tldr
Clone the repo
git clone --depth 1 https://github.com/pehcastro/harness

Or install brevity, the plugin that ships this one along with the rest of its 1 skill, 1 command, 1 agent, 2 hooks.

Wrote 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.

agentmods badge for tldr

README.md
[![agentmods](https://agentmods.dev/badge/commands/pehcastro/harness/tldr.svg)](https://agentmods.dev/commands/pehcastro/harness/tldr)
Your own site
<a href="https://agentmods.dev/commands/pehcastro/harness/tldr"><img src="https://agentmods.dev/badge/commands/pehcastro/harness/tldr.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 537 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00029 $0.00537
Opus 5 $0.00015 $0.00269
Sonnet 5 $0.00006 $0.00107
Haiku 4.5 $0.00003 $0.00054

Measured 5d ago against content hash 2f8881918cc8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

tldr 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 5d 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.

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/brevity/commands/tldr.md · 72 lines

What it actually says

tldr

Compress recent output into a TLDR. The reader has already read it and wants the short version, so the summary is the whole reply.

What to summarise

Read $ARGUMENTS.

Argument Summarise
empty Your last reply
session Everything since the session started
last N Your last N replies
anything else Treat it as the subject and summarise what was said about it

Shape

Answer with the summary alone. No heading, no preamble, no offer to expand. The reader asked for the short version, so a TLDR label on a reply that is entirely a TLDR is noise.

Caps: 40 words for the last reply, 150 for a session. Both are hard.

What survives compression

Keep, in this order of priority:

  1. The decision the reader has to make, and the options.
  2. Anything still open or unanswered.
  3. A risk, and anything that cannot be undone.
  4. Numbers the reader needs: a count, a file path, an identifier.
  5. What changed, when the reader cannot see it.

Drop everything else. Reasoning, evidence, how you got there, and what you tried first are all gone. If it survives the cut it was not decoration.

Rules that still apply

Every rule in the output style holds here, since this is chat output like any other. No banned words, no em dash, no preamble, no closing offer.

One that matters more than usual: do not restate what the reader watched. A session TLDR is not a list of every command you ran. It is where things stand now.

Examples

A long reply about a failing lookup:

Not the lookup. No user with id `A` is seeded, so /users/A 404s correctly.
Decide: seed a user `A`, or make the lookup case-insensitive.

A session that built an API:

Hono API in `src/`, 5 tests passing. Store is an in-memory Map, so it
resets on restart. Two open: whether the 404 body should include the id,
and whether to persist before the demo.

When the reader wants more

They will ask. Do not offer.

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.

  1. 5d ago First seen · 72 lines · 29 tokens per session scan A 2f8881918cc8

Subscribe to this mod's changes

tldr is a command published in the GitHub repository pehcastro/harness (1 stars, last pushed 18d ago), licensed MIT. It adds 29 tokens to every session and 537 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.