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 evidencegit 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/evidence)<a href="https://agentmods.dev/skills/leewayworks/guochuang-gps/evidence"><img src="https://agentmods.dev/badge/skills/leewayworks/guochuang-gps/evidence/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/evidence"><img src="https://agentmods.dev/badge/skills/leewayworks/guochuang-gps/evidence.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 | $0.00555 |
| Opus 5 | $0.00018 | $0.00278 |
| Sonnet 5 | $0.00007 | $0.00111 |
| Haiku 4.5 | $0.00004 | $0.00056 |
Grade A, and why
evidence 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.
How it starts
The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evidence
Apply the shared policies in gps-common. When saving a Markdown report, use the common project-name rule with topic 证据.
Build a material map that lets another person find and inspect the support for every important claim. A polished slide and a path string are leads until their contents are checked.
Own this work
Own source status, claim links, file existence, locators, evidence roles, independence, contradictions and redaction. Do not decide the project's positioning or improve a weak claim by rewriting it more confidently.
Validate sources
Use this state sequence:
missing -> user_asserted -> located -> inspected -> verified | contradicted
For a local source, resolve a relative path against the project JSON file or declared project root. Give it no verified credit if the file does not exist. For a URL, record when and how it was inspected; a verified string does not prove that a page was opened.
A file that exists is located, not automatically verified. For image-only PDF or PPTX pages, record visual_review_required and the page or slide.
Build the ledger
Use one row per claim and include:
id, claim, source, page_or_slide, source_level, status, date, owner, metric_unit, baseline, condition, limitation, evidence_role, independence_group, ownership_scope, customer_stage, privacy_flag.
Use evidence roles problem, mechanism, result, independent_validation and persistence. Two records from the same independence_group count as one corroborating source. A quantitative claim needs a claim ID plus a locator or test condition before it can reach high evidence quality.
Cross-check
Compare numbers, units, dates, names, IP ownership, customer stage, team roles and project titles across the project book, deck, script and raw records. Return the contradiction instead of selecting the nicer value.
Keep contact, intent, pilot, contract, paid and repeat separate. Do not turn a logo, invitation or intention letter into a paid customer result. Do not use a patent or paper as proof of product performance, adoption or student ownership without the corresponding links.
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 · 43 lines · 37 tokens per session scan A 067400772151
evidence 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 555 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
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
overleaf-sync
A two-way connection between a local paper folder and Overleaf, a web-based LaTeX editor for writing research papers. It lets you move changes between the local files and the shared Overleaf project.