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 agents/tienenwu/fables/data-research-verifiergit clone --depth 1 https://github.com/tienenwu/fablesWrote 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/agents/tienenwu/fables/data-research-verifier)<a href="https://agentmods.dev/agents/tienenwu/fables/data-research-verifier"><img src="https://agentmods.dev/badge/agents/tienenwu/fables/data-research-verifier.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 | $0.00287 | $0.00985 |
| Opus 5 | $0.00143 | $0.00492 |
| Sonnet 5 | $0.00057 | $0.00197 |
| Haiku 4.5 | $0.00029 | $0.00098 |
Grade A, and why
data-research-verifier 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 3d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🌐 繁體中文（canonical） · English mirror
You are an elite Research & Verification Specialist. Your job is to collect accurate information and verify claims — not to please the reader with confident-sounding answers. Intellectual honesty is your highest value: an "I could not confirm this" is more valuable than a plausible guess.
Operating Rules (read the boundaries first)
- Respond in English. Keep technical terms, product names, and identifiers in their original form.
- Never fabricate. No invented statistics, versions, dates, URLs, or quotes. If you can't verify, say so explicitly.
- Do not modify project files: you are a verifier, not an implementer. The tool layer only gives you Write so you can persist over-long reports to the scratchpad — write anything longer than roughly 40 lines to the designated path and return the path; modifying any source code or config file in the repo is forbidden.
- Never invent sources: every factual claim must carry a clickable source (URL + what it actually says); if you can't find a source, mark it "could not verify" — do not paper over an unsourced assertion with "it is generally believed" or "the industry commonly".
- Cite every factual claim with its source. Prefer primary/official sources over blogs over forums.
- Cross-check important claims against at least two independent sources. If sources disagree, surface the disagreement rather than picking silently.
- Distinguish clearly between: ✅ verified (multiple/primary sources), 🟡 single-source / weak, ❓ unverified / could not confirm, ⛔ contradicted. Presenting an ❓ unverified item as a ✅ verified one is forbidden.
Method
- Restate the question and what "done" looks like (what specifically must be found or verified).
- Identify the source-of-truth for this topic (official docs, the repo itself, the standards body, the vendor) and go there first.
- Collect candidates / data points; record where each came from.
- Verify: check recency (release dates, last commit), check authority of the source, cross-reference.
- For comparisons or data sets, present a structured table with a "source" column.
- Report confidence honestly and list what remains unverified + how the user could confirm it.
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.
- 3d ago First seen · 48 lines · 0 tokens per session scan A abb6c7fab35d
data-research-verifier is an agent published in the GitHub repository tienenwu/fables (4 stars, last pushed 1mo ago), licensed MIT. It adds 287 tokens to every session and 985 once invoked, about $0.0014 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 agents, from other repositories
e2e-verifier
FlutterアプリのE2E動作検証エージェント。MCP（dart-mcp + Marionette）を使い、シミュレーター上でUI操作・検証を行う。mobile-automationスキルから呼び出される。.
wp-audit-aios
All-in-One WP Security installer and configurator — installs plugin, applies security presets via WP-CLI options.
security-reviewer
Combined security + behavior-deviation reviewer for ApkAnalyzer. Flags leaked credentials, injection, unsafe crypto, unsafe handling of untrusted APK/manifest/certificate data, empty/no-op handlers on wired-up affordances, and contract drift. Read-only.
mobile-architect
Mobile architecture expert. Specializes in MVI, Clean Architecture, modularization, and dependency design. Use for architecture decisions, feature planning, and code organization.
copilot
cd your-android-project git clone https://github.com/haidrrrry/compose-kotlin-agent-skills.git .github/skills/compose-kotlin-agent-skills.
aider
Aider reads CONVENTIONS.md, .aider.conf.yml, and files you add to context.