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 leewayworks/guochuang-gps --skill proposalgit clone --depth 1 https://github.com/leewayworks/guochuang-gpsWrote 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/leewayworks/guochuang-gps/proposal)<a href="https://agentmods.dev/skills/leewayworks/guochuang-gps/proposal"><img src="https://agentmods.dev/badge/skills/leewayworks/guochuang-gps/proposal/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/leewayworks/guochuang-gps/proposal"><img src="https://agentmods.dev/badge/skills/leewayworks/guochuang-gps/proposal.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 | $0.00033 | $0.00524 |
| Opus 5 | $0.00016 | $0.00262 |
| Sonnet 5 | $0.00007 | $0.00105 |
| Haiku 4.5 | $0.00003 | $0.00052 |
Grade A, and why
proposal 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 9d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Proposal
Apply the shared policies in gps-common. When saving a Markdown report, use the common project-name rule with topic 项目书.
A project book should let a reviewer follow the argument and check the important claims. Start with the argument map, then revise prose.
Working spine
Adapt this pattern to the track and project maturity:
project snapshot -> context and need -> field research -> development path -> problem / intervention / metric -> product and use -> alternatives -> IP and results -> validation and adoption -> student contribution -> business model -> finance and risk -> social value -> plan.
This is a pattern learned from historical 国创赛, 大挑 and 小挑 materials. It is not a 2026 page limit or template.
Maturity lanes
- Idea: establish the user, problem, field evidence and first test.
- Prototype: show the mechanism, baseline, test condition and failure cases.
- Pilot: show user acceptance, repeatability, delivery path and ownership.
- Revenue: separate paid transactions from forecasts, margins and scale assumptions.
Do not let a revenue-style section hide an untested prototype. Do not let a technical section omit who will use the result.
Section audit
For every heading record: section_claim, why_now, evidence_ids, quantified_result, student_contribution, limitation and bridge_to_next.
Use TBD (owner, date) for an open fact. Keep a revision queue ordered by claim risk, not by page order.
Rewrite pattern
Write each important paragraph as: problem -> user or setting -> intervention -> measured change -> proof -> limitation.
Replace claims such as "internationally leading" or "first" with a comparison table that names the baseline, metric, condition, sample and source. Keep marketing language only after the evidence is visible.
Track lenses
- Higher-education creative or venture: research depth, innovation, student ownership and industry value.
- Red-tour (青年红色筑梦之旅): participation, field work, beneficiary change, sustainability and the operating mechanism.
- Industry: enterprise question, response fit, demonstrator, implementation and acceptance evidence.
- Vocational or sprout: craft, practice, autonomy, growth and eligibility.
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.
- 9d ago First seen · 51 lines · 33 tokens per session scan A 3e862b52cde1
proposal is a skill published in the GitHub repository leewayworks/guochuang-gps (6 stars, last pushed 26d ago), licensed MIT. It adds 33 tokens to every session and 524 once invoked, about $0.0002 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 2026-08-31.
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…
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…