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 SisyphusSQ/harness-template --skill issue-goal-promptgit clone --depth 1 https://github.com/SisyphusSQ/harness-templateWrote 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/sisyphussq/harness-template/issue-goal-prompt)<a href="https://agentmods.dev/skills/sisyphussq/harness-template/issue-goal-prompt"><img src="https://agentmods.dev/badge/skills/sisyphussq/harness-template/issue-goal-prompt/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/sisyphussq/harness-template/issue-goal-prompt"><img src="https://agentmods.dev/badge/skills/sisyphussq/harness-template/issue-goal-prompt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00052 | $0.00684 |
| Opus 5 | $0.00026 | $0.00342 |
| Sonnet 5 | $0.00010 | $0.00137 |
| Haiku 4.5 | $0.00005 | $0.00068 |
Grade A, and why
issue-goal-prompt 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 11d 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
任务目标提示词
为任务生成具体目标提示词。除非用户明确要求继续实施，否则只生成提示词，不执行任务实现。
必要输入
issue_id、任务链接或仓库内任务文件路径；- 可选约束：执行模式、范围限制、来源文档、验证策略、分支 / 提交 / 推送边界、多仓范围。
如果没有任务标识或来源文档，先询问用户。否则从当前仓库、Issue provider 和用户提供的来源中自行发现细节。
真相来源
生成提示词前先读取或检查：
AGENTS.md；.agents/PLANS.md与相关计划（如存在）；.agents/state/、.agents/runs/中与本任务相关的本地摘要（如存在）；- 任务正文、评论、标签 / 状态和链接的来源文档；
- 用户点名的设计文档、接口文档或测试手册。
如果真相来源冲突，协作状态以 Issue provider 为准，执行约束以仓库文档和代码为准。未能自行消解的冲突必须写进生成的提示词。
生成流程
基于当前真相生成目标提示词，不只依赖记忆：
- 提取目标、包含范围、排除范围、验收标准、来源文档、验证命令、停止条件、依赖 / 阻塞；
- 对复杂任务建议先创建或更新
.agents/plans/YYYY-MM-DD-<slug>.md； - 明确每个会写入的仓库、目录和文件范围；
- 明确是否允许 commit、push、merge 或外部系统写入；
- 给出实现步骤、验证步骤、恢复点和下一步；
- 只在任务本身需要时加入 review、live 或外部回写要求，不自动引入额外流程。
状态文件规则
组装提示词后统计字符数：
- 如果提示词
<= 4000字符，直接返回完整提示词； - 如果提示词
> 4000字符，把完整提示词写入.agents/state/GOAL-<ISSUE-ID>.md； - 如果状态文件已经存在，先读取并保留仍然有效的恢复字段，再更新目标提示词、时间、恢复点和下一步。
默认 .gitignore 会忽略真实 .agents/state/* 文件。如果用户要求提交生成的 Goal 文件，必须先确认项目确实需要跟踪它。
输出规则
- 只输出生成的完整目标提示词或短启动提示词；
- 在短启动提示词中使用绝对路径；
- 不包含隐藏推理；
- 只生成提示词时，不实施、不提交、不推送、不合并，也不修改 Issue 状态。
What ships with it
2 files 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.
- 11d ago First seen · 56 lines · 52 tokens per session scan A 9581d1e8421d
issue-goal-prompt is a skill published in the GitHub repository SisyphusSQ/harness-template (11 stars, last pushed 19d ago), licensed MIT. It adds 52 tokens to every session and 684 once invoked, about $0.0003 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
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…