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/injaytseng/graph-engineering-on-research/first-graphnpx skills add InjayTseng/graph-engineering-on-research --skill first-graphgit clone --depth 1 https://github.com/InjayTseng/graph-engineering-on-researchWrote 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/injaytseng/graph-engineering-on-research/first-graph)<a href="https://agentmods.dev/skills/injaytseng/graph-engineering-on-research/first-graph"><img src="https://agentmods.dev/badge/skills/injaytseng/graph-engineering-on-research/first-graph.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 | $0.00033 | $0.00292 |
| Opus 5 | $0.00016 | $0.00146 |
| Sonnet 5 | $0.00007 | $0.00058 |
| Haiku 4.5 | $0.00003 | $0.00029 |
Grade A, and why
first-graph 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 4d 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
Read ${CLAUDE_PLUGIN_ROOT}/prompts/00-first-graph.md. Everything below its "## Copy this block" line is your instruction set — execute it exactly, with one substitution: the "My claim:" slot at the end is filled by the user's input below.
My claim: $ARGUMENTS
Harness rules:
- If the claim above is empty, ask the user for one sentence they currently believe and act on — do not invent a claim.
- If the claim above is written in Chinese, use
${CLAUDE_PLUGIN_ROOT}/prompts/00-first-graph.zh-TW.mdinstead (its block starts at "## 複製這段", the slot is "我的主張：") and work in Traditional Chinese throughout. - You can spawn subagents: each of the three skeptics MUST be a separate subagent with fresh context that never sees the others' output. Never simulate the skeptics sequentially in this context.
- When the template's closing mentions templates 02 and 03 by name, they are installed alongside this one:
/diamond-researchand/adversarial-review.
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.
- 4d ago First seen · 18 lines · 33 tokens per session scan A ce4134e44e6d
first-graph is a skill published in the GitHub repository InjayTseng/graph-engineering-on-research (10 stars, last pushed 4d ago), licensed MIT. It adds 33 tokens to every session and 292 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
coach
Progressive help for any topic. Repeat to go deeper: concept -> procedural -> reference. Triggers on: coach, learn, explain, teach me, tell me more, how does, what is, go deeper.
lookup
Look up help topics with progressive depth. Pair with attune-ai for the full author-and-read workflow. Triggers on: lookup, look up, depth, topic, help topic, tell me more.
lookup-list
List all available help topics, optionally filtered by tag. Use to browse what's in the bundled templates or the project's .help/ directory. Triggers on: list topics, what's available, browse help, show topics.
lookup-topic
Look up a help topic with progressive depth. First call returns concept, repeat calls escalate to task then reference. Triggers on: look up topic, open template, tell me more, go deeper, start over.
lookup-warn
Get context warnings for a file based on its extension and name. Surfaces known gotchas before the user hits them. Triggers on: warn me, gotchas, pitfalls, what should I watch out for, check this file.
asa-reader-layer-writer
Use when turning structured skill decomposition artifacts into beginner, expert, report, or Obsidian reading layers.