fact-driven-batch

A workflow for processing a host-managed batch through a fixed Agent Graph. A batch is a group of related items handled together, while the host controls which targets and handlers are used.

In plain words
What is it for?
Evaluating the assigned graph, resolving its main route, reading required resources, and delegating work to the integration host.
Why use it?
It ensures required context is read and that the host can refresh the facts after each action instead of relying on stale information.

Skill for Claude CodeCodex

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 skills/context4ai/agent-graph/operator
Any agent
npx skills add context4ai/agent-graph --skill operator
Clone the repo
git clone --depth 1 https://github.com/context4ai/agent-graph

Made for: Claude Code, Codex.

Per session 16 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 98 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 $0.00016 $0.00098
Opus 5 $0.00008 $0.00049
Sonnet 5 $0.00003 $0.00020
Haiku 4.5 $0.00002 $0.00010

Measured yesterday against content hash 9efd99968562, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fact-driven-batch 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 yesterday.

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.

examples/fact-driven-batch/skills/operator/SKILL.md · 15 lines

What it actually says

Fact-driven batch

Evaluate the bound graph, resolve its primary route, read required resources marked read-required, and delegate host handlers to the integration host. The host owns target selection and refreshes Facts after every action.

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. yesterday First seen · 15 lines · 16 tokens per session scan A 9efd99968562

Subscribe to this mod's changes

fact-driven-batch is a skill published in the GitHub repository context4ai/agent-graph (12 stars, last pushed yesterday), licensed MIT. It adds 16 tokens to every session and 98 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 2026-08-30.