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 defensegit 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/defense)<a href="https://agentmods.dev/skills/leewayworks/guochuang-gps/defense"><img src="https://agentmods.dev/badge/skills/leewayworks/guochuang-gps/defense/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/defense"><img src="https://agentmods.dev/badge/skills/leewayworks/guochuang-gps/defense.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 | $0.00037 | $0.00438 |
| Opus 5 | $0.00018 | $0.00219 |
| Sonnet 5 | $0.00007 | $0.00088 |
| Haiku 4.5 | $0.00004 | $0.00044 |
Grade A, and why
defense 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 10d 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
Defense
Apply the shared policies in gps-common. When saving a Markdown report, use the common project-name rule with topic 答辩.
Rehearse the questions that can change a reviewer's decision. Challenge the strongest claim and the weakest proof. Answers must come from records, not improvised facts.
Question matrix
Generate questions across need, method, novelty, measurement, customer, economics, IP, team contribution, risk and social value.
Add track questions for red-tour field impact, industry command fit and demonstrator, vocational practice, or sprout autonomy. Add stage pressure for school review, provincial review and national final.
Answer card
Use this order:
direct answer -> evidence pointer -> boundary or limitation -> next action.
Each card also records severity, speaker, screen_evidence, verification_owner and verification_date. If the team does not know, say what is unknown and give a check owner and date. Never hide a material risk or coach a fabricated answer.
Scoring the drill
Score each answer from 0 to 2 on:
- Clarity: the first sentence answers the question.
- Evidence: the pointer can be opened or shown.
- Ownership: the student explains their own work.
- Boundary: limitations and conditions are stated.
A score of 6 or less is a revision item. A missing source or integrity issue is a hard stop regardless of fluency.
Drill modes
Return a severity-ranked question set and choose a mode:
- Script run: timed opening, transitions and close.
- Interrupt run: stop after each claim and ask for its source.
- Adversarial run: combine a strong claim, a missing control and a time limit.
Include the local time limit only when supplied by an official or local notice. The output should contain the script, interrupt points, screen evidence list, failed cards and the next rehearsal date. Passing a drill means understandable and auditable. It does not predict an award.
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.
- 10d ago First seen · 46 lines · 37 tokens per session scan A 0da0438d1862
defense is a skill published in the GitHub repository leewayworks/guochuang-gps (6 stars, last pushed 28d ago), licensed MIT. It adds 37 tokens to every session and 438 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.