Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Gingiris-1031/gingiris-skillsnpx agentmods add skills/gingiris-1031/gingiris-skills/gr-readmeWrote 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/gingiris-1031/gingiris-skills/gr-readme)<a href="https://agentmods.dev/skills/gingiris-1031/gingiris-skills/gr-readme"><img src="https://agentmods.dev/badge/skills/gingiris-1031/gingiris-skills/gr-readme.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 325 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 660 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium Agent Snooping · line 347 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Data Exfiltration · line 390 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 468 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00458 | $0.07221 |
| Opus 5 | $0.00229 | $0.03610 |
| Sonnet 5 | $0.00092 | $0.01444 |
| Haiku 4.5 | $0.00046 | $0.00722 |
Grade A, and why
gr-readme 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 — 722 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub README Writing System
Built from taking AFFiNE from 0 to 60K stars. The README didn't just describe the product — it was the product for the first 30 days.
— (AFFiNE case, Iris Wei @WeiYipei, ep01/ep03/ep06)
双重视角 / Dual Frame: README Writing = Skill Description Writing
One insight from Claude Code Skills that applies directly to README craft:
"Claude uses the
descriptionfield to decide when to apply the skill."
A README's tagline works by exactly the same logic: a one-sentence description that makes the right reader self-select in. If Claude can't tell from your skill's description when to use it, visitors can't tell from your README why they need it.
The table below maps the parallel:
| README element | Skill frontmatter field | Shared principle |
|---|---|---|
| Tagline (first line) | description first sentence |
Specific, scannable, triggers the right reader |
| Sub-description (2–3 sentences) | description body |
Problem + solution + differentiator |
| Trigger phrases in README | when_to_use |
Disambiguation — when to use this, not something else |
| Architecture/How it works | Supporting files (reference.md) |
Detail on demand, not always in context |
| Quick Start commands | allowed-tools + shell blocks |
Concrete, executable, verifiable |
This frame is not a metaphor — it's a practical test. If you can't write a one-sentence tagline for your README that passes the same bar as a skill's description, the README needs more work.
核心原则 / Core Principles
Principle 1: README is your product's first landing page
The README has one job: convert a GitHub visitor into a star, fork, or install within 3 seconds of first scroll. Everything else is secondary.
Principle 2: A weak product can still have a great README
AFFiNE 开源时产品还是「套壳」demo，README 写对了照样火。 — (AFFiNE case, Iris Wei @WeiYipei, ep03/ep06)
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 First seen · 722 lines · 458 tokens per session scan A 9d6072a61102
gr-readme is a skill published in the GitHub repository Gingiris-1031/gingiris-skills (79 stars, last pushed 3d ago), licensed MIT. It adds 458 tokens to every session and 7,221 once invoked, about $0.0023 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
oss-launch
Use when taking a repo open source, or hardening one that already is. Run /oss-launch and it scans the repo (stack, existing files, git remote, secrets), asks only what it cannot infer, then generates a tailored OSS file collection (README, LICENSE, CONTRIBUTING, CODEOFCONDUCT, SECURITY, CHANGELOG, .gitignore…
diagrams
Mermaid diagrams following the C4 model: context, container, component, sequence, ER and deployment. Use when saying "diagram", "visualize", or "architecture diagram".
keep-the-why
Extract and preserve the reasoning code cannot explain - decisions, rejected alternatives, workarounds, incidents, constraints - plus project setup and maintainer interviews. Not for what changed (see Keep a Changelog) - only why.
review
Adversarial fresh-context review of an increment before it ships. Every finding cites path:line and is re-verified. Use when saying "review", "grill this", or "critique the implementation".
sw-do
Implement a SpecWeave increment task by task through the ledger, with evidence per task and a verified close. Use for "implement this", "start working", "continue the increment", "keep going".
done
Close an increment: ledger check, specweave verify, optional review, then specweave complete. Use when all tasks are done and saying "close increment", "we are done", or "finish up".