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 agentmods add skills/eph5xx/tweakidea/ti-reportnpx skills add eph5xx/tweakidea --skill ti-reportgit clone --depth 1 https://github.com/eph5xx/tweakideaWrote 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/eph5xx/tweakidea/ti-report)<a href="https://agentmods.dev/skills/eph5xx/tweakidea/ti-report"><img src="https://agentmods.dev/badge/skills/eph5xx/tweakidea/ti-report.svg" alt="Measured on agentmods" 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 | $0.00018 | $0.01654 |
| Opus 5 | $0.00009 | $0.00827 |
| Sonnet 5 | $0.00004 | $0.00331 |
| Haiku 4.5 | $0.00002 | $0.00165 |
Grade A, and why
ti-report 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 6d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reference files for rendering styled evaluation reports via scripts/render_report.py.
Not directly invoked by Claude — consumed by the script layer only.
Files
| File | Purpose |
|---|---|
template.html.j2 |
Jinja2 HTML template. Rendered with autoescape=True to prevent XSS from idea text / LLM prose. Notion-style layout with sticky topbar, hero stats, dim-grid, collapsible per-dimension detail rows, tabbed research highlights, reach-potential callout, and dark-mode toggle. |
template.md.j2 |
Jinja2 markdown template. Rendered with autoescape=False so raw markdown symbols (>, —, ` |
styles.css |
All CSS rules extracted from the sample mock verbatim. Read at render time by render_report.py and inlined into a <style> tag in report.html (portable single-file artifact). Uses CSS custom properties for theming; [data-theme="dark"] flips the palette. |
SKILL.md |
This file. Documents files, rendering contract, and data extraction contract. |
Dual-Environment Rendering Contract
scripts/render_report.py builds two Jinja2 environments sharing the same FileSystemLoader:
from jinja2 import Environment, FileSystemLoader, select_autoescape
loader = FileSystemLoader(str(TI_REPORT_DIR))
html_env = Environment(
loader=loader,
autoescape=True, # force escaping for this env
trim_blocks=True,
lstrip_blocks=True,
)
md_env = Environment(
loader=loader,
autoescape=False,
trim_blocks=True,
lstrip_blocks=True,
)
Pitfall 2 warning: Do NOT use select_autoescape(["html", "htm"]) — template.html.j2 ends in .j2 and would not be matched. The html_env must use autoescape=True directly to guarantee HTML escaping regardless of filename.
The CSS is passed as a template variable css:
data["css"] = (TI_REPORT_DIR / "styles.css").read_text()
What ships with it
3 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.
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.
- 6d ago First seen · 97 lines · 18 tokens per session scan A f63e8685e8a2
ti-report is a skill published in the GitHub repository eph5xx/tweakidea (48 stars, last pushed 4mo ago), licensed MIT. It adds 18 tokens to every session and 1,654 once invoked, about $0.0001 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
gr-competitor
竞品深度扫描。批量抓取对手落地页（title/h1/intro/pricing）、定价页、博客 top 10、 变更历史（Wayback）。底层调 actionbook（并发 30 tab + 省 90% token）。 当用户说"分析对手"、"看看竞品在做啥"、"找对标"、"扫一下 top 10"时调用。.
idea-validator
Giúp đánh giá một ý tưởng có đáng thử hay không cho mục đích kinh doanh hoặc học tập, dựa trên bằng chứng, nguồn lực thực tế và một bước thử có giới hạn. Dùng khi cần xem nhanh, phân tích đầy đủ, so sánh ý tưởng hoặc xem lại báo cáo cũ.
idea-to-mvp
Take a rough idea from the user (a few lines of text), summarize it, then act as a domain-expert product manager to interactively refine it into a full requirement document and MVP plan. Use when someone says "I have an idea", "help me build X", "turn this into a product", "what would the MVP look like", or provides a…
venture-architect
Autonomous end-to-end venture pipeline that transforms a raw idea into a complete set of venture artifacts in a single execution loop. Triggers when the user says "this is an idea", "I have a venture idea", "here's a concept", "turn this into a venture", or presents any raw startup/product idea for full-stack…
pmf-advisor
You are a product-market fit advisor with a mandate to challenge, not validate. Your default posture is skepticism. You have seen founders mistake good marketing for PMF, mistake a vocal minority for the market, and mistake retention of the wrong customers for product success. You apply rigorous frameworks and refuse…
idea-validator
Validate startup ideas using Hexa's Opportunity Memo framework and Perceived Created Value (PCV) methodology. Assess problem-solution fit, market opportunity, and determine if an idea is worth pursuing.