Borrowing it
Nothing to install: this file belongs to swimmwatch/cloakbrowser-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/swimmwatch/cloakbrowser-mcp/main/.agents/skills/planning-and-task-breakdown/SKILL.mdgit clone --depth 1 https://github.com/swimmwatch/cloakbrowser-mcpWrote 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/swimmwatch/cloakbrowser-mcp/planning-and-task-breakdown)<a href="https://agentmods.dev/skills/swimmwatch/cloakbrowser-mcp/planning-and-task-breakdown"><img src="https://agentmods.dev/badge/skills/swimmwatch/cloakbrowser-mcp/planning-and-task-breakdown/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/swimmwatch/cloakbrowser-mcp/planning-and-task-breakdown"><img src="https://agentmods.dev/badge/skills/swimmwatch/cloakbrowser-mcp/planning-and-task-breakdown.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 | $0.00089 | $0.00617 |
| Opus 5 | $0.00044 | $0.00309 |
| Sonnet 5 | $0.00018 | $0.00123 |
| Haiku 4.5 | $0.00009 | $0.00062 |
Grade A, and why
planning-and-task-breakdown 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 12d 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
Planning And Task Breakdown
Create the smallest safe, reviewable plan. Task packets are the executable
artifacts; plan.md is only their compact index.
- Read
AGENTS.md,.agents/references/task-packets.md, the request, current worktree, approveddocs/specs/<slug>/spec.md, its decision ledger, and relevant code, tests, docs, package metadata, and workflows. Use CodeGraph before broad source search when indexed. - For substantial work, require
Status: Approved. If the specification is missing, draft, materially incomplete, or contradicted by current public contracts, return the work to/spec. - Inspect requirement identifiers and repository evidence before reading targeted prose. Do not edit production, test, public documentation, package, Docker, or workflow implementation while planning.
- Use explicit user decisions and repository evidence. Start or reopen a
persistent Prompt MCP interview such as
plan:<spec-slug>for unresolved material planning choices. Return contract-changing questions to/spec. - State outcome, non-goals, relevant contracts, assumptions, risks, dependency order, rollback, verification, and manual gates.
- Create and maintain:
docs/specs/<slug>/tasks/plan.md;docs/specs/<slug>/tasks/todo.md;docs/specs/<slug>/tasks/handoff.md;- one
docs/specs/<slug>/tasks/NN_<task>.mdper independent task.
- Make each packet self-contained according to
.agents/references/task-packets.md. Map every requirement to at least one packet; map shared requirements deliberately rather than leaving them implicit. - Separate changes so each packet has one outcome, owned file boundaries,
objective acceptance, focused checks, failure/rollback behavior, and a
useful stopping point. Label external, destructive, credentialed, merge,
publish, and release actions
MANUAL GATE. - Checkpoint
approval.planorauthorization.executionand ask a separate Prompt MCP question when plan approval or implementation authorization is required. An approved specification does not authorize implementation. - Finish the packet set and stop. Do not implement, format unrelated files, commit, push, open a PR, publish, release, or start the first packet.
This skill is the single authoritative /plan route. Do not create a second
slash-command implementation.
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.
- 12d ago First seen · 47 lines · 89 tokens per session scan A 5491e4157f1a
planning-and-task-breakdown is a skill published in the GitHub repository swimmwatch/cloakbrowser-mcp (57 stars, last pushed yesterday), licensed MIT. It adds 89 tokens to every session and 617 once invoked, about $0.0004 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.
Other skills, from other repositories
browser-search
Multi-engine web search (SearXNG) + browsing/scraping (Camofox, CloakBrowser). Use whenever you need to do web research.
x402
Set up Browser Use Cloud payments with x402 — pay per request from a crypto wallet (USDC on Base mainnet), no signup or API key. Two setups it works out up front — "just use it" (set up a wallet so you or Claude Code can run cloud browser tasks paid from the wallet — Claude writes and runs throwaway scripts, nothing…
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.
open-source
Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that imports from browseruse, asks about @sandbox deployment, supported LLM models, Actor API, custom tools, lifecycle…
opencli-autofix
Automatically fix broken OpenCLI adapters when commands fail. Load this skill when an opencli command fails — it guides you through collecting a trace artifact, patching the adapter, retrying, and filing an upstream GitHub issue after a verified fix. Works with any AI agent.
opencli-usage
Use at the start of any OpenCLI session — this is the top-level map of what opencli can do, how to discover adapters, what flags and output formats are universal, and which specialized skill to load next. Point here when an agent asks "what can opencli do?" or "how do I find the right command?".