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 debug-plangit 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/debug-plan)<a href="https://agentmods.dev/skills/cloudflare/agents/debug-plan"><img src="https://agentmods.dev/badge/skills/cloudflare/agents/debug-plan/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/debug-plan"><img src="https://agentmods.dev/badge/skills/cloudflare/agents/debug-plan.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 | $0.00030 | $0.00135 |
| Opus 5.5 | $0.00012 | $0.00054 |
| Sonnet 5.5 | $0.00006 | $0.00027 |
| Haiku 4.5 | $0.00003 | $0.00014 |
Grade A, and why
debug-plan 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 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.
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.
What it actually says
Debug Plan
Create a practical debugging plan that starts with evidence before fixes.
Instructions
- Restate the symptom in one sentence.
- List the most likely failure boundaries.
- Suggest the first three checks in order.
- Identify what evidence would confirm or reject each hypothesis.
- End with the smallest safe fix path.
Keep the plan short enough that someone can start immediately.
For more detail on the shape of the output, read
references/checklist.md.
What ships with it
1 file 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.
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 · 22 lines · 30 tokens per session scan A 3e81306b58ec
debug-plan is a skill published in the GitHub repository cloudflare/agents (5,841 stars, last pushed today), licensed MIT. It adds 30 tokens to every session and 135 once invoked, about $0.0001 per session on Opus 5.5. 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.
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.
longstrider
Longstrider is the optimization spell for systems that already work. It makes the path shorter without changing the destination. It cares about sustained pace, not flashy one-off benchmarks.
mage-hand
Use this skill for small, careful remote manipulations where dexterity matters more than force.
blindness-deafness
In D&D, Blindness/Deafness selectively removes one sense — the target can still act but loses critical awareness. The real-world version is selective channel muting: blocking a process from seeing certain inputs (input filtering, API response redaction), deafening it to specific signals (suppressing webhooks, ignoring…
eyebite
In D&D, Eyebite lets you focus on one creature per turn and inflict sleep, panic, or sickness through sustained eye contact. The real-world version is targeted capability reduction: focused analysis that identifies and disables specific functions of a system, service, or adversary. Feature flagging a dangerous…
power-word-kill
In D&D, Power Word Kill instantly destroys any creature below a hit-point threshold — no saving throw, no resistance, just death. The real-world version is kill -9: the unconditional termination signal. Emergency circuit breakers. Hard account terminations. The nuclear option that exists because sometimes graceful…