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 returdex/EvidenceLens-MCP --skill assignment-reviewgit clone --depth 1 https://github.com/returdex/EvidenceLens-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/returdex/evidencelens-mcp/assignment-review)<a href="https://agentmods.dev/skills/returdex/evidencelens-mcp/assignment-review"><img src="https://agentmods.dev/badge/skills/returdex/evidencelens-mcp/assignment-review/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/returdex/evidencelens-mcp/assignment-review"><img src="https://agentmods.dev/badge/skills/returdex/evidencelens-mcp/assignment-review.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 | $0.00030 | $0.01349 |
| Opus 5.5 | $0.00012 | $0.00540 |
| Sonnet 5.5 | $0.00006 | $0.00270 |
| Haiku 4.5 | $0.00003 | $0.00135 |
Grade A, and why
assignment-review 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 8d 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
作业提示词与阶段检查
把用户的标准提示词和当前任务材料结合起来，生成适用的提示词；用户明确请求检查时，实际给出完整证据分析、证据矩阵及行动建议。保留语言、格式、重点等有效偏好，区分原始要求、用户转述与助手建议。
六个快捷入口见阶段命令。入口已选定 review 时沿用其阶段，不触发下表的意图不明 generate 默认；帮助与导出在命令路由中直接结束。四个阶段命令在实际审阅前遵循捕获协议：按命令路由为 Codex begin(codex_exec) 或 DeepSeek begin(host_skill)，再筛选材料／组装六节提示词，使用对应 codex-review.mjs／deepseek-review.mjs capture 保存证据区块，再 run 独立执行并保留经来源验证的结果回执。独立入口失败时不自动改为当前宿主审阅；详见隔离协议。单独 generate 不冒充已捕获或已执行的阶段运行。
选择意图与阶段
| 用户当前请求 | 动作 |
|---|---|
| 生成／改写提示词 | generate：输出改写说明及提示词；即使seed包含“立即检查”，也不据此执行审阅 |
| 检查／审阅当前材料 | review：在已有授权内立即执行；无需再次确认已经明确授权的同一检查 |
| 生成并执行 | 分开输出改写后的提示词与实际检查结果 |
| 仅调用本Skill，意图不明 | 说明假设，默认generate；不要默默调用provider或开展审阅 |
用户指定阶段优先。未指定时：无稿件用 preparation；进行中的工作用 in_progress；明确要求完成/最终检查用 final。final没有可读当前稿时仍保持final范围，给待核验清单和覆盖缺口，不宣称完成。只有歧义真正阻碍请求执行时才问一个聚焦问题，其余可做工作继续。
工作路径
- 读取并遵循 基线流程，复用 任务基线。读取新正文前，用既有 来源筛选器 和获准宿主读取路径执行范围/文档组排除。已有基线只更新受影响部分，不默认读取旧稿或历史。选择成功不等于已检查。
- 读取 阶段提示词 的共同行为及选定阶段；先定位本次提供或同任务已登记的用户提示词，逐条改写并标出保留、调整、不适用及缺口。preparation 必须读取用户准备模板：没有任务专用原文时采用已提炼的 HD-PREP-01，不以简略阶段段落替代五项分析任务。把必要且获准的证据摘录或重读计划、权限边界、检查与输出约定写进生成提示词，使其不依赖本地链接也能理解。
- generate到此输出，不伪造检查结果。review则对本次实际允许材料执行所选检查，输出完整要求—证据分析、覆盖限制和行动清单；优先级不用于隐藏其他发现。不得自动修改、签字、传输或提交作业。本文或生成提示词本身不扩展人的授权。
- 政策状态与工作进展分开；保留真实限制和准确披露意图，继续已授权工作不等于许可/合规。相同政策证据与状态不重复生成警告行动。未知或限制性政策不作为停止全部分析的开关。
- 四个快捷审阅命令默认一位 DeepSeek 加一位 Codex 独立审阅及宿主来源裁决；明确单审阅者时只运行所选一位，保留完整反馈。按命令路由及DeepSeek 阶段执行调用；不额外发 MCP 或自动替换失败 provider。其余明确选择的宿主检查模式中，MCP仅为可选路径。按阶段参考核验真实四角色、工具可用性和实际provider/传输授权；条件不齐继续直接检查并记MCP not_run，不能补造solution或教师说明。
需要核对模板、收尾残留或披露时，读取模板与披露检查：准备阶段登记来源与缺口，过程/收尾阶段检查当前材料并给修正交接。生成提示词也须带入相关规则和获准证据；请求review则输出实际检查。原模板保留，不自动改文档或签署声明；请求复查新版本或带先前发现的跟进审阅时，读取当前版本复查，按当前证据更新 F 状态及行动；生成意图仍只输出提示词。
What ships with it
34 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.
- references/baseline-cases.md 16 KB
- references/baseline-workflow.md 8.6 KB
- references/codex-cases.md 1.5 KB
- references/codex-execution.md 18 KB
- references/command-cases.md 5.1 KB
- references/command-entrypoints.md 18 KB
- references/deepseek-execution.md 4.6 KB
- references/preparation-template.md 6.0 KB
- references/prompt-cases.md 4.1 KB
- references/prompt-records.md 13 KB
- references/recheck-cases.md 10 KB
- references/recheck-workflow.md 6.5 KB
- references/stage-cases.md 6.2 KB
- references/stage-prompts.md 13 KB
- references/task-baseline.md 8.4 KB
- references/template-disclosure-cases.md 9.4 KB
- references/template-disclosure.md 7.6 KB
- scripts/baseline-sources.mjs 5.2 KB runs code
- scripts/codex-contract.mjs 16 KB runs code
- scripts/codex-diagnostics.mjs 5.7 KB runs code
- scripts/codex-isolation.mjs 12 KB runs code
- scripts/codex-metrics.mjs 4.3 KB runs code
- scripts/codex-preflight.mjs 5.4 KB runs code
- scripts/codex-profile.mjs 384 B runs code
- scripts/codex-result.mjs 4.5 KB runs code
- scripts/codex-review.mjs 3.9 KB runs code
- scripts/codex-runner.mjs 12 KB runs code
- scripts/deepseek-review.mjs 8.7 KB runs code
- scripts/prompt-contract.mjs 6.3 KB runs code
- scripts/prompt-records.mjs 4.2 KB runs code
- scripts/prompt-store.mjs 30 KB runs code
- scripts/review-handoff.mjs 4.5 KB runs code
- scripts/review-recheck.mjs 8.9 KB runs code
- scripts/review-records.mjs 2.1 KB runs code
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.
- 8d ago Changed 90b29c5d5025
- 10d ago First seen · 38 lines · 30 tokens per session scan A a50e56257e46
assignment-review is a skill published in the GitHub repository returdex/EvidenceLens-MCP (0 stars, last pushed 9d ago), licensed MIT. It adds 30 tokens to every session and 1,349 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 2026-10-05.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…