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 genli-ai/market-research-skills --skill verifyinggit clone --depth 1 https://github.com/genli-ai/market-research-skillsWrote 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/genli-ai/market-research-skills/verifying)<a href="https://agentmods.dev/skills/genli-ai/market-research-skills/verifying"><img src="https://agentmods.dev/badge/skills/genli-ai/market-research-skills/verifying/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/genli-ai/market-research-skills/verifying"><img src="https://agentmods.dev/badge/skills/genli-ai/market-research-skills/verifying.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 | $0.00214 | $0.05476 |
| Opus 5 | $0.00107 | $0.02738 |
| Sonnet 5 | $0.00043 | $0.01095 |
| Haiku 4.5 | $0.00021 | $0.00548 |
Grade A, and why
verifying 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 13d 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 — 361 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Information Verification Skill
Bilingual skill. Chinese version:
SKILL.zh.md. English is the single source of truth; the.zh.mdis a synchronized translation — always edit the English first, then mirror the change into.zh.mdin the same change-set, never edit only the Chinese.
Purpose
The user provides a sentence or paragraph that needs verification. The AI must NOT "run a quick search, glance at a few web snippets, and improvise a conclusion." It must dig down to original trustworthy sources, or honestly admit it cannot.
Five scenarios are covered:
- Basic truthfulness check: whether the numbers / facts / quotes in the statement are accurate.
- Completeness: when the source is correct but the user's quotation is out of context — supply the missing context.
- One-level reasoning verification: when a direct number cannot be traced to a primary source, cross-check via metric decomposition (Z = P × Q).
- Negative statements: detect unfalsifiable claims like "X has never done Y" and switch to a "search for a counter-example" path.
- Multi-source conflict: when two authoritative sources disagree on the same figure, present them side-by-side with a difference attribution.
Input
The user supplies one statement (or paragraph) to verify. Optional attachments (PDFs, links, screenshots, notes) take priority as material to verify against.
Scope exclusions (refused topics)
Before any verification work begins, check whether the statement falls into a refused category. The following topics are out of scope regardless of how the request is phrased or how specific the question is:
- Political issues — elections, parties, political figures' positions, geopolitical disputes, government legitimacy debates, etc.
- Military issues — military operations, force composition, equipment counts, conflict details, defense policy, etc.
- Religious issues — doctrines, denominational disputes, religious leaders' statements, inter-faith comparisons, etc.
- Entertainment celebrity gossip — personal lives, relationships, family affairs, paparazzi rumors, etc.
- Other inherently controversial topics — even attempting verification can be inflammatory regardless of what the answer turns out to be.
What ships with it
2 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.
- 13d ago First seen · 361 lines · 214 tokens per session scan A 0d4742154f82
verifying is a skill published in the GitHub repository genli-ai/market-research-skills (62 stars, last pushed 3mo ago), licensed MIT. It adds 214 tokens to every session and 5,476 once invoked, about $0.0011 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
mobile-store-review
Audits a mobile app codebase — Expo/React Native (managed or bare) or native iOS/Android, standalone or inside a Turborepo/monorepo — and reports whether it would pass Apple App Review and Google Play review. Use this skill whenever the user: asks if their app will pass, fail, or get rejected by Apple or Google…
pr-review
Reviews a branch, PR, staged, or working-tree diff for correctness, security, repo-convention, test-coverage, and documentation gaps, returning severity-rated findings without editing code. Use when asked to "review my branch/PR", "is this ready to merge", "check this diff before I push", "does this need an ADR", or…
rest-api-design
Designs and reviews REST APIs: resource naming, HTTP methods and status codes, payload and error formats, pagination, versioning, auth, rate limiting, and OpenAPI specs. Use when adding or renaming an endpoint, asked "is this endpoint RESTful", "what status code should I return", "design the API for X", or to audit an…
create-pr
Opens (or updates) a pull request with a conventional title, an evidence-backed description, and a real verification checklist — resolving the base branch from evidence, attaching screenshots via the GitHub CLI when the change is visible in the UI, and asking rather than guessing at every genuine judgment call. Use…
decision-record
Writes or updates an architecture decision record (ADR) as a dated markdown file under docs/decision-records/ — a one-sentence declarative title with no leading number and no Status field, and the four sections Context, Decision, Consequences, Related. Use when a change makes a real judgment call with a defensible…
commit
Commits everything modified or new in the working tree by default, grouped into a series of coherent Conventional Commits — one commit per logical change, staged by path, with the type/scope vocabulary inferred from the repo's own git history — instead of sweeping everything into a single commit. Configurable per repo…