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 reproducegit 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/reproduce)<a href="https://agentmods.dev/skills/cloudflare/agents/reproduce"><img src="https://agentmods.dev/badge/skills/cloudflare/agents/reproduce/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/reproduce"><img src="https://agentmods.dev/badge/skills/cloudflare/agents/reproduce.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 302 Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.Fix: Limit tool chaining depth and validate the output of each tool before passing it to the next. Require explicit user approval for multi-step chains.
- high Privilege Escalation · line 298 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium MCP Rug Pull · line 104 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 246 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.03761 |
| Opus 5.5 | $0.00016 | $0.01504 |
| Sonnet 5.5 | $0.00008 | $0.00752 |
| Haiku 4.5 | $0.00004 | $0.00376 |
Grade C, and why
reproduce scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
cd /workspace && rm -rf "$PUBLISH_DIR" 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 — 350 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/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
Reproduce the bug end-to-end and post your findings as an issue comment.
The instruction is the free-form text the user typed after @agent-think (it
may be empty). Treat it as an extra hint from the triggering user
— e.g. additional reproduction steps, a specific version, or a pointer to the
suspect area. Let it guide your reproduction, but the issue itself remains the
source of truth.
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).
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 --depth=1 https://github.com/<repo>.git "$REPO_DIR"
fi
1. Understand the issue
gh issue view <issueNumber> --repo <repo> --json title,body,labels,comments
Read it carefully. Extract:
- the observed behavior (the bug),
- the expected behavior,
- any "To Reproduce" steps, code snippets, versions, or stack traces.
Decide if it is reproducible at all. If it is a feature request, a question,
a pure-docs issue, or has no concrete runnable behavior, stop here: return
skipped: true, reproduced: false, and a summary explaining why. Still post
a short, polite comment saying the repro-agent skipped it and why; begin it with
Requested by @<requestedBy> when the run envelope has a requester.
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 · 350 lines · 40 tokens per session scan C 70bf6ecdb16c
reproduce is a skill published in the GitHub repository cloudflare/agents (5,836 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 3,761 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 2 findings (recursive force delete, 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
workers-profiling
Profile or debug CPU usage and memory allocation in deployed Cloudflare Workers and Durable Objects. Then use this information to optimize your code.
azure-kubernetes-automatic-readiness
Assess Kubernetes workloads and cluster configuration for AKS Automatic compatibility. Identifies incompatibilities, generates fixes, and guides migration from AKS Standard to AKS Automatic. WHEN: migrate to AKS Automatic, check AKS Automatic readiness, validate manifests for Automatic, assess cluster for Automatic…
agents-sdk
Build, debug, or review Cloudflare Agents SDK applications using the agents package.
cloudflare-one-migrations
Assess and plan migrations from existing VPN, SWG, or SASE platforms to Cloudflare One, including policy mapping, parity gaps, and rollout.
sandbox-stable
Build or maintain Cloudflare Sandbox apps on the stable @cloudflare/sandbox package. Use sandbox-next for preview apps and sandbox-migrate-to-next for stable-to-preview migrations.
sandbox-migrate-to-next
Migrate Cloudflare Sandbox apps from stable @cloudflare/sandbox to @cloudflare/sandbox@next (SDK 1.0 preview). Use sandbox-next for apps already on the preview.