SkillAgentSearch skills...

agency-os

Notion-as-source-of-truth dispatch board for running your work like an AI agency. One Tasks database is the source of truth; tasks flow Suggestion through Discussion, To-Do, In Progress, and Done with subtasks, recurring cadences, dependencies, and template subtrees.

Install / Use

npx skills add jeremylongshore/tons-of-skills-marketplace --skill agency-os

Installs into whichever agent you are using.

About this skill
๐Ÿ“„

SKILL.md

Installable skill definition

Quality Score

91/100

Supported Platforms

Universal

Our assessment of agency-os

agency-os scores 91/100 on our quality scale, 181st of 606 Data & Analytics skills we index (top 30%).

Its SKILL.md is 7.3 KB long, well organised into 9 sections with 3 code examples: a thorough specification that gives an agent plenty to work with.

With 2,785 GitHub stars, it is one of the more widely adopted skills in the catalogue.

Substance
29/30
Structure
18/20
Description
15/15
Adoption
15/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated about 2 months ago, so agency-os is actively maintained.
  • Our last check on 2026-10-28 found the source still online.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit โ€” read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-09-30. Automated pattern scan on 2026-09-29. It catches known dangerous patterns, not every risk โ€” read a skill before letting an agent act on it.

agency-os compared with similar skills

All 4 of these similar skills score higher than agency-os; compare them before choosing.

SkillScoreStarsUpdatedFormat
agency-os (this skill)by jeremylongshore912.8k53d agoSKILL.md
x402by browser-use100121.0k3d agoSKILL.md
algorithmic-artby anthropics100177.9k55d agoSKILL.md
pptxby anthropics100177.9k55d agoSKILL.md
designby nextlevelbuilder100149.0k6d agoSKILL.md

Frequently asked questions

How do I install agency-os?
Run npx skills add jeremylongshore/tons-of-skills-marketplace --skill agency-os. The install tabs above show the steps for each supported agent.
Which AI agents does agency-os work with?
It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
Is agency-os safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is agency-os still maintained?
The repository was last updated about 2 months ago, so agency-os is actively maintained.

name: agency-os description: | Notion-as-source-of-truth dispatch board for running your work like an AI agency. One Tasks database is the source of truth; tasks flow Suggestion through Discussion, To-Do, In Progress, and Done with subtasks, recurring cadences, dependencies, and template subtrees. Batch execution fans approved To-Do rows out to parallel agents with per-task model selection. Use when capturing chat to Notion, running the To-Do queue, suggesting, approving, or discussing tasks, or coordinating multi-task batches. Trigger with "/agency-os" subcommands or natural-language variants ("add a suggestion: โ€ฆ", "let's discuss X", "run the queue"). allowed-tools: Read, Write, Edit, Bash(python3:), Bash(npx:), Glob, Grep version: 0.2.0 author: ratamaha-git ratamaha@automatelab.tech license: MIT compatibility: Designed for Claude Code; requires the Notion MCP server (@notionhq/notion-mcp-server) and a Notion workspace with a Tasks database tags: [ai-agency, notion, orchestration, mcp, dispatch, parallel-execution]

agency-os

Notion-as-source-of-truth dispatch board. One Tasks database, one Hub page, one page per Corpus, one page each for General Guidance and Resources. The skill mutates Notion via the Notion MCP (mcp__*__notion-* tools); only references/notion-pointers.json is committed to git.

Skill name decision: the skill is named agency-os (matching the repo). All commands are /agency-os <cmd>. This is the single plugin entry point; there is no agency-os/notion sub-namespace. If you embed this plugin alongside others, prefix commands with agency-os to avoid collisions.

Overview

agency-os turns a single Notion database into a multi-status dispatch board for AI work. The model is intentionally narrow:

  • One Tasks database is the source of truth for status, priority, model selection, and ownership. No parallel kanban tools.
  • One Hub page holds the General Guidance, Resources, and Corpus pointers that every task consults.
  • Tasks flow through five statuses: Suggestion โ†’ Discussion โ†’ To-Do โ†’ In Progress โ†’ Done. The dedup gate at each transition prevents accidental re-execution.
  • run fans approved To-Do rows out to parallel agents. Each task carries its own model selection (Haiku for cheap fan-out, Sonnet for default, Opus for hard reasoning) and respects declared dependencies.

The skill is stateless on disk โ€” the only committed artifact is references/notion-pointers.json (database/page IDs). All runtime state lives in Notion.

For the full architecture (status flow, sync protocol, workspace structure, pointer/cache format), see references/architecture.md.

Prerequisites

  • Notion MCP server installed: npx -y @notionhq/notion-mcp-server (declare in .mcp.json)
  • Notion integration token (NOTION_TOKEN) with read+write access to your workspace. Add .env to .gitignore โ€” never commit the token.
  • A Notion Tasks database with the columns the skill expects (see references/architecture.md ยง "Workspace structure" for the schema). The /agency-os init command can scaffold this for you.
  • Python 3 for the optional scripts/query-tasks.py helper.

First-time setup:

ccpi install agency-os
# then in Claude Code:
/agency-os init --harness=basic --haiku=cost-tier --sonnet=default --opus=hard-reasoning

Instructions

The skill is a CLI surface over Notion. Three usage patterns:

  1. Direct command invocation โ€” /agency-os <cmd> [args]. See references/commands.md for the full reference of 19 commands (init, scaffold, suggest, discuss, log, add-subtask, approve, start, refresh, run, done, kill, next, status, list, show, update, move, plus launch alias).

  2. Natural-language driving โ€” the skill translates conversational chat into the corresponding command. Examples in references/natural-language.md.

  3. Batch execution โ€” /agency-os run [--go] fans the entire To-Do queue out to parallel agents with per-task model selection. See ## Examples below for the canonical flow.

Status flow is enforced โ€” you cannot skip a stage. Every command performs a sync preflight to ensure your local view of Notion is current (see references/architecture.md ยง "Sync โ€” preflight on every command").

When drafting any user-facing copy (READMEs, blog posts, launch surfaces), apply the positioning brief at references/positioning.md before writing.

Output

Every command returns to chat with:

  • Verdict line โ€” โœ… <action> or โš ๏ธ <reason> (one line, scannable)
  • Affected task IDs and titles โ€” every task touched, with its new status
  • Next-action hint โ€” what command the operator would typically run next

Batch run additionally emits:

  • A per-task pass/fail table
  • Total model spend estimate (Haiku/Sonnet/Opus call counts)
  • Outstanding-dependency callouts for tasks that couldn't start

Error Handling

The skill fails closed on five well-defined cases (full details in references/architecture.md ยง "Status flow โ€” the dedup gate"):

| Condition | Behavior | |---|---| | Notion API auth fails | Halt, print "NOTION_TOKEN missing or invalid", exit 1 | | Database/page ID drift (pointers stale) | Halt, print "Run /agency-os refresh", exit 1 | | Status-flow violation (e.g. approve on a Suggestion) | Halt with the required prerequisite step quoted | | Dependency cycle detected during run | Halt, list the cycle, exit 1 | | Task missing required model selection | Halt, print "Run /agency-os update <id> --model <tier>" |

The skill never silently corrects state in Notion โ€” every fix is an explicit command the operator must run.

Examples

Capture a chat insight as a Suggestion:

User: add a suggestion: refactor the auth flow to use the new token cache
Skill: โ†’ /agency-os suggest "refactor the auth flow to use the new token cache"
       โœ… Created Suggestion #t-2026-05-23-001 in corpus "platform"
       Next: /agency-os discuss t-2026-05-23-001

Approve and run a batch:

User: approve t-2026-05-23-{001..003} then run the queue
Skill: โœ… Approved 3 tasks โ†’ To-Do
       /agency-os run --go
       โ†’ fanning to 3 parallel agents...
       โœ… Done: 2 | โš ๏ธ Blocked on deps: 1 | Total spend: ~$0.04

More examples and the full command catalog are in references/commands.md.

Resources

  • Plugin source: https://github.com/ratamaha-git/agency-os
  • Launch post: https://automatelab.tech/agency-os-launch/
  • references/architecture.md โ€” status flow, sync protocol, workspace schema
  • references/commands.md โ€” full CLI reference (19 commands)
  • references/natural-language.md โ€” chat-to-command translation table
  • references/positioning.md โ€” canonical brief for user-facing copy
  • references/general-guidance.md โ€” shared operating principles applied to every task
  • references/notion-pointers.json โ€” pointer file scaffold (database/page IDs)
  • references/task-page-template.md โ€” Notion page template for new tasks
  • references/corpus-template.md โ€” Notion page template for a Corpus
  • references/config-template.json โ€” default per-task model routing
  • scripts/query-tasks.py โ€” optional Python helper for offline introspection

Related Skills

View on GitHub
GitHub Stars2.8k
CategoryData
Updated1mo ago
Forks404

Languages

Python

Trust signals

100/100

From repository metadata: license, adoption, age and documentation. Not a code audit โ€” see the Safety scan above for what the skill file itself contains.

No cautions
agency-os โ€” Universal Skill: Install & Safety Check | SkillAgent