agency

agency is a skill for Claude Code, Codex from runxhq/runx. It costs 53 tokens per session (1,505 once invoked), scanned A, original, Apache-2.0.

A governed team process that keeps a fixed group, a continuing objective, and a case record across separate turns. Each turn chooses and records one approved action.

In plain words
What is it for?
Use it to coordinate several agents on a case, enforce escalation and spending limits, and keep a replayable record until the case is resolved.
Why use it?
It prevents delegation from becoming open-ended or untraceable. The work stays within defined member permissions and can be reviewed afterward.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to coordinate several agents on a case, enforce escalation and spending limits, and keep a replayable record until the case is resolved.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/runxhq/runx/agency
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 runxhq/runx --skill agency
Clone the repo
git clone --depth 1 https://github.com/runxhq/runx

Made for: Claude Code, Codex.

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 agency

README.md
[![agentmods](https://agentmods.dev/badge/skills/runxhq/runx/agency.svg)](https://agentmods.dev/skills/runxhq/runx/agency)
Your own site
<a href="https://agentmods.dev/skills/runxhq/runx/agency"><img src="https://agentmods.dev/badge/skills/runxhq/runx/agency.svg" alt="Measured on agentmods" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,505 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00053 $0.01505
Opus 5 $0.00026 $0.00753
Sonnet 5 $0.00011 $0.00301
Haiku 4.5 $0.00005 $0.00151

Measured 8d ago against content hash 2c5e1c0bcf57, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

agency 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 8d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (graph/plan/plan.mjs, graph/reduce/reduce.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/agency/SKILL.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agency

Run a standing, accountable team toward a mandate, one governed turn at a time.

An agency is the only runx skill that holds a roster, a persistent objective, and a case that spans turns. It is a governed delegation envelope: a defined set of members with scope ceilings, a mandate, cumulative limits, and a case whose every turn is sealed and replayable. It composes the existing skills and reimplements none. Each turn borrows ops-desk for judgment, the roster members for execution, data-store for the event log, and receipts for the ledger.

It is not a durable-execution engine and it is not an autonomous daemon. One turn is one stateless governed act; an external driver (a human, a cron, a board poll) runs the loop by calling advance until the case resolves.

Composes

  • data-store#append_event
  • data-store#read_events
  • ops-desk#advance

What this skill does

  • open starts a case: it appends opened with the mandate, the roster, and the cumulative limits snapshot, so the charter travels with the case.
  • advance runs one turn: it folds the case from its event stream, asks ops-desk for the single next move constrained to the roster, enforces the measurable gate, records one turn event whose append is the contention lease, and names the member to run. The member runs as a separate governed run; its outcome is fed back to the next advance as member_result.
  • status folds and returns the current case state.

The case reducer is the agency's own code, because data-store carries events but does not fold domain state. Everything else is delegation.

When to use this skill

  • A standing, consequential mandate must run for days or weeks, dispatch different members, and leave an auditable trail sealed to a bounded authority.
  • A process needs scoped delegation with a measurable ceiling and a human gate on consequence, not an unbounded agent.

Read the full file on GitHub · 147 lines

Files

What ships with it

8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 8d ago First seen · 147 lines · 53 tokens per session scan A 2c5e1c0bcf57

Subscribe to this mod's changes

agency is a skill published in the GitHub repository runxhq/runx (84 stars, last pushed today), licensed Apache-2.0. It adds 53 tokens to every session and 1,505 once invoked, about $0.0003 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 2026-08-30.