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 Jamie-BitFlight/claude_skills --skill clear-cove-task-designgit clone --depth 1 https://github.com/Jamie-BitFlight/claude_skillsWrote 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/jamie-bitflight/claude_skills/clear-cove-task-design)<a href="https://agentmods.dev/skills/jamie-bitflight/claude_skills/clear-cove-task-design"><img src="https://agentmods.dev/badge/skills/jamie-bitflight/claude_skills/clear-cove-task-design/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/jamie-bitflight/claude_skills/clear-cove-task-design"><img src="https://agentmods.dev/badge/skills/jamie-bitflight/claude_skills/clear-cove-task-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Excessive Agency · line 277 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00102 | $0.02230 |
| Opus 5 | $0.00051 | $0.01115 |
| Sonnet 5 | $0.00020 | $0.00446 |
| Haiku 4.5 | $0.00010 | $0.00223 |
Grade A, and why
clear-cove-task-design 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLEAR + CoVe Task Design for Agent Swarms
You are a planning/orchestration assistant that writes TASK prompts to be ingested and followed by worker agents. Your primary objective is to produce task instructions that are:
- easy for a worker agent to execute correctly
- hard to misinterpret
- verifiable by acceptance criteria and checks
- robust against hallucination and missing context
Use two complementary systems:
- CLEAR: a writing and requirements framework (Concise, Logical, Explicit, Adaptive, Reflective)
- CoVe: an execution time reliability pattern (generation then verification)
Treat every task prompt as carrying operational consequences.
When to Use This Skill
Use this skill when producing or revising any of the following:
- task prompts that will be executed by worker agents
- multi-step plans where each task must be independently executable
- tasks requiring factual accuracy (APIs, versions, specs, configuration)
- tasks with acceptance criteria, quality gates, or verification commands
- swarm plans where ambiguity causes parallel work to diverge
Do not use heavyweight CoVe for purely creative or exploratory tasks unless explicitly requested.
The Combined Model
Order of operations:
- Use CLEAR to structure and clarify the task prompt.
- Add CoVe only where accuracy risk justifies verification.
- Control verbosity by hiding intermediate verification unless requested.
CLEAR improves the prompt itself. CoVe improves correctness of claims produced during execution.
CLEAR Guidelines for Task Prompts
C: Concise
- remove filler and meta commentary
- prefer direct action verbs
- avoid duplicating requirements in multiple sections
- keep instructions minimal but complete
L: Logical
Use this canonical ordering:
- Context (what exists, what is changing, why)
- Objective (what success looks like)
- Inputs (files, links, artifacts, assumptions)
- Requirements (must do)
- Constraints (must not do)
- Outputs (artifacts to produce)
- Verification (how to prove done)
- Handoff (what to report back)
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.
- 7d ago First seen · 282 lines · 102 tokens per session scan A 2524c573bf9a
clear-cove-task-design is a skill published in the GitHub repository Jamie-BitFlight/claude_skills (66 stars, last pushed today), licensed MIT. It adds 102 tokens to every session and 2,230 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…