Cloudflare Agents is a framework for building persistent, stateful AI agents on Cloudflare Durable Objects, where each agent has its own state, storage, and lifecycle. Developers use it to create agents with real-time communication, scheduling, model calls, MCP, workflows, and other server-side capabilities. The catalogue entries provide agent, skill, MCP, and instruction components for this framework.
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.
npx skills add cloudflare/agents --skill open-prgit clone --depth 1 https://github.com/cloudflare/agentsWrote 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.
[](https://agentmods.dev/skills/cloudflare/agents/open-pr)<a href="https://agentmods.dev/skills/cloudflare/agents/open-pr"><img src="https://agentmods.dev/badge/skills/cloudflare/agents/open-pr/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/cloudflare/agents/open-pr"><img src="https://agentmods.dev/badge/skills/cloudflare/agents/open-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00040 | $0.02108 |
| Opus 5.5 | $0.00016 | $0.00843 |
| Sonnet 5.5 | $0.00008 | $0.00422 |
| Haiku 4.5 | $0.00004 | $0.00211 |
Grade A, and why
open-pr scanned grade A with 1 finding 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
All `gh`, `git`, `npm`, `curl`, and `wrangler` commands must run on the How it starts
The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The current user message contains an <agent-think-run> envelope with
repository, issue, instruction, requested-by, and (when available)
trigger-comment-id.
Use those values exactly. Never infer or substitute another target from examples,
workspace contents, GitHub searches, or concurrent issues. If the envelope or a
required field is absent, stop without cloning/editing/pushing/posting and return a
structured skipped result. When trigger-comment-id is present, your first
container action is the liveness reaction:
gh api repos/<repository>/issues/comments/<trigger-comment-id>/reactions \
-f content=rocket
Produce a focused fix PR, authored as yourself — the agent-think GitHub App. Do not impersonate any user.
The instruction is the free-form text the user typed after @agent-think (it
may be empty). Treat it as a direct instruction — e.g. constraints
on the fix, a preferred approach, or a pointer to the suspect area — and weight
it highly, but stay within the scope of the issue.
All gh, git, npm, curl, and wrangler commands must run on the
container backend (bash({ command, backend: "container" })) — the shell
backend has no real binaries or network. gh is already authenticated as the
app; use it directly (no token handling). Work under /workspace; put long
logs and disposable scratch files in container-local /temp.
0. Clone the repo
Clone the target repo directly under /workspace using its repository name
(cloudflare/agents → /workspace/agents):
REPO_DIR="/workspace/$(basename <repo>)"
if [ ! -d "$REPO_DIR/.git" ]; then
git clone https://github.com/<repo>.git "$REPO_DIR"
fi
cd "$REPO_DIR"
1. Gather everything known
gh issue view <issueNumber> --repo <repo> --json title,body,labels,author,comments
Read the body and every comment. In particular look for a comment from the
prior repro run (@agent-think repro): it may contain a minimal reproduction, a live URL,
observed-vs-expected behavior, and a root-cause hypothesis pointing at a
file/line. Use it as your starting point — do not re-derive what is already
known.
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.
- 1mo ago First seen · 208 lines · 40 tokens per session scan A 78d45c10481b
open-pr is a skill published in the GitHub repository cloudflare/agents (5,857 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 2,108 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
uploads-cli
Reference for the uploads CLI and its stdio/hosted MCP tools — exact flags, keys, and contracts for put and attach, screenshot capture, stable PR/issue keys, the managed attachments comment, metadata and search, galleries, change feeds (repo-wide or one PR/issue), config defaults, login/doctor, and output formats. Use…
github-screenshots
Embed screenshots, images, diagrams, GIFs, and screen recordings in GitHub PRs and issues — or stage them ahead of a PR, collect them into one attachments comment, or get a durable public link to share a visual with a person. Use this whenever a visual needs to end up in a PR description, issue body, or PR/issue…
speak-with-dead
This spell is archaeology, not history research. It operates on specific artifacts from a specific dead system to answer specific questions. It is NOT general tech history, NOT interviewing living people, and NOT monitoring live systems.
dimension-door
Dimension Door is the quick-switch spell: branch to branch, environment to environment, project to project. It is not a migration and it is not discovery. It assumes both endpoints are known, prepared, and close enough in shape that you can step across with only the context you actually need.
history
In D&D, History recalls significant past events, legendary figures, and ancient knowledge. The real-world version is temporal investigation: git blame across the entire project, reading changelogs to understand why a decision was made, reconstructing the sequence of events that led to a production incident, or…
agent-framework-py-release
Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…