agent-brief

agent-brief is a skill for Claude Code from sleeyax/promptfiles. It costs 44 tokens per session (876 once invoked), scanned A, original, MIT.

A renderer that turns discussion, an issue, or a session into a durable implementation brief for another coding agent.

In plain words
What is it for?
It is for writing testable specifications for issues, handoffs, and cloud-agent tasks.
Why use it?
It preserves the required behavior and acceptance checks in a self-contained form, so work can be handed off without relying on the original conversation.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Part of the sleeyax-skills plugin — 17 skills, 2 agents shipped together

Good fit It is for writing testable specifications for issues, handoffs, and cloud-agent tasks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sleeyax/promptfiles/agent-brief
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.

Any agent
npx skills add sleeyax/promptfiles --skill agent-brief
Clone the repo
git clone --depth 1 https://github.com/sleeyax/promptfiles

Made for: Claude Code.

Or install sleeyax-skills, the plugin that ships this one along with the rest of its 17 skills, 2 agents.

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 agent-brief

README.md
[![agentmods](https://agentmods.dev/badge/skills/sleeyax/promptfiles/agent-brief.svg)](https://agentmods.dev/skills/sleeyax/promptfiles/agent-brief)
Your own site
<a href="https://agentmods.dev/skills/sleeyax/promptfiles/agent-brief"><img src="https://agentmods.dev/badge/skills/sleeyax/promptfiles/agent-brief.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 876 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00044 $0.00876
Opus 5 $0.00022 $0.00438
Sonnet 5 $0.00009 $0.00175
Haiku 4.5 $0.00004 $0.00088

Measured 7d ago against content hash d50754439b7b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

agent-brief 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 7d 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.

skills/delegation/agent-brief/SKILL.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Brief

Source (optional): $ARGUMENTS

Render a brief that another agent implements from. The brief is the contract: whatever discussion, issue thread, or session produced it is context, but the brief is what gets built.

This skill is a renderer, not an investigator. It never interviews the user, never explores the codebase on its own initiative, and never writes to a tracker — it returns markdown, and whoever called it decides where that lands. Invoked directly (/agent-brief), the source is the current conversation.

Principles

  • Durable — the brief may sit for weeks while the codebase moves. Describe interfaces, types, and behavioral contracts. Never reference file paths or line numbers, and don't assume today's implementation structure survives.
  • Behavioral, not procedural — say what the system should do. The implementing agent explores fresh and decides how.
  • Testable — every acceptance criterion must be independently verifiable. "Works correctly" is not a criterion.
  • Self-contained — the brief is usually read on a tracker, where the repo's glossary isn't. Use the project's terms, but define any whose meaning a newcomer would guess wrong, and point at CONTEXT.md for the rest.

Template

The heading is always ## Agent Brief, unchanged, so a brief stays recognizable when something re-reads it later.

Each section carries a rule for when it applies. Drop the ones whose rule isn't met — an empty heading is noise.

## Agent Brief

**Summary:** one line — what needs to happen

**Context:**
Why this is being asked for; the problem behind it.

**Current behavior:**
What happens today.

**Starting point:**
Which branch to continue from and what's already on it.

**Desired behavior:**
What should happen once the work is done, including edge cases and error handling.

**Key interfaces:**
- `TypeName` — what changes and why
- `functionName()` — current contract vs desired contract

**Decisions already made:**
- decision — and the reason, so it doesn't get relitigated

**Agent's discretion:**
- open question the implementing agent resolves itself, plus any constraint it must respect

**Acceptance criteria:**
- [ ] specific, independently verifiable criterion

**Out of scope:**
- adjacent thing that must not change

Read the full file on GitHub · 87 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.

  1. 7d ago First seen · 87 lines · 44 tokens per session scan A d50754439b7b

Subscribe to this mod's changes

agent-brief is a skill published in the GitHub repository sleeyax/promptfiles (2 stars, last pushed 9d ago), licensed MIT. It adds 44 tokens to every session and 876 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 103 tokens

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…

microsoft/vscode · 72 tokens

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…

openai/codex · 114 tokens