An agent-role manifest that defines the structure, responsibilities, tools, triggers, and rules for a multi-agent briefing workflow. A multi-agent workflow splits a larger job among specialized agents.

It is for configuring roles such as scouting, analysis, editing, auditing, formatting, coordination, and quality checks.

It gives the workflow a shared contract, so each agent knows its role and the expected handoffs.

manifest — Agent for coding agents by Stahl-G: An agent-role manifest that defines the structure, responsibilities, tools…

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 agents/stahl-g/briefloop/manifest

Clone the repo

git clone --depth 1 https://github.com/Stahl-G/briefloop

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/stahl-g/briefloop/manifest.svg)](https://agentmods.dev/agents/stahl-g/briefloop/manifest)

Your own site

<a href="https://agentmods.dev/agents/stahl-g/briefloop/manifest"><img src="https://agentmods.dev/badge/agents/stahl-g/briefloop/manifest.svg" alt="Measured on agentmods" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 355 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	$0.00000	$0.00355
Opus 5	$0.00000	$0.00178
Sonnet 5	$0.00000	$0.00071
Haiku 4.5	$0.00000	$0.00036

Measured 4d ago against content hash 76565aa289cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

manifest 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 4d 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.

docs/agents/manifest.md · 66 lines

What it actually says

Agent Roles Manifest

Schema

configs/agent_roles.yaml

Schema version: multi-agent-brief-agent-roles/v1

Structure

schema_version: "..."
project:
  name: "..."
  purpose: "..."
  workflow: [...]
  output_contract: [...]
  non_goals: [...]
tool_profiles:
  read_only: { ... }
  edit_safe: { ... }
  audit_read_only: { ... }
  audit_edit: { ... }
roles:
  <role-name>:
    stage: workflow | harness | coordination
    tool_profile: <profile-name>
    description: "..."
    trigger: "..."
    responsibilities: [...]
    hard_rules: [...]

Subagent workflow

Default: Scout (discover + screen) -> Claim Ledger -> Analyst -> Delivery Editor -> Auditor -> Formatter
Strict: Scout -> Screener -> Claim Ledger -> Analyst -> Delivery Editor -> Auditor -> Formatter

Subagent workflow Roles

scout (pipeline)
screener (pipeline)
claim-ledger (pipeline)
analyst (pipeline)
auditor (pipeline)
editor (pipeline)
formatter (pipeline)

Harness Roles

draft-audit-harness (harness)
final-quality-harness (harness)
rendered-output-harness (harness)

Coordination Roles

orchestrator (coordination)
source-provider (coordination)
source-planner (coordination)

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.

4d ago First seen · 66 lines · 0 tokens per session scan A 76565aa289cc

Subscribe to this mod's changes

manifest is an agent published in the GitHub repository Stahl-G/briefloop (9 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 355 tokens. 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.

Building agents Productivity Writing and docs ai-agents audit briefing business claim-ledger evidence

cee-briefing-agent

The reporting and alignment agent for the Chief Execution Engine. Handles two cadences: (1) Morning Focus Briefing — a daily scannable 5-section brief rendered at session start; (2) Weekly Alignment Audit — a structured 7-phase review of tasks, OKRs, and project health status.

sanchitnis/SrujanaSangama · 68 tokens

hormozi-orchestrator

Master offer-building orchestrator inspired by Alex Hormozi's frameworks. Captures raw ideas, notes, or existing offers from the user, interviews them to extract market, problem, outcome, and constraints, then routes to specialized subagents to produce offer documents. Use when user wants to build an offer, validate a…

alexsmedile/hormozi-skills · 98 tokens

manifest