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/theaisingularity/agentic-research-engine-oss/verify-answernpx skills add TheAiSingularity/agentic-research-engine-oss --skill verify-answergit clone --depth 1 https://github.com/TheAiSingularity/agentic-research-engine-ossWrote 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/theaisingularity/agentic-research-engine-oss/verify-answer)<a href="https://agentmods.dev/skills/theaisingularity/agentic-research-engine-oss/verify-answer"><img src="https://agentmods.dev/badge/skills/theaisingularity/agentic-research-engine-oss/verify-answer.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 | $0.00066 | $0.01720 |
| Opus 5 | $0.00033 | $0.00860 |
| Sonnet 5 | $0.00013 | $0.00344 |
| Haiku 4.5 | $0.00007 | $0.00172 |
Grade A, and why
verify-answer 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.
How it starts
The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
verify-answer
Decomposes an answer into atomic factual claims and checks each against the evidence the user provides. Returns a clean per-claim report so the user can see exactly what the answer got right, what it got wrong, and what the sources didn't cover.
This skill is prompt-only — no tools, no network, no MCP server required. It works in any Claude installation. Built on the Chain-of-Verification pattern (Dhuliawala et al., 2023).
Looking for the automated version? The full
agentic-research-engine-osspipeline runs this verification step automatically after every synthesized answer, sources included. Install withpip install agentic-research-engineor/plugin marketplace add https://github.com/TheAiSingularity/agentic-research-engine-oss.
How to use
Paste an answer and the sources it cites, then invoke:
/verify-answer
Or ask in plain English: "verify this," "fact-check these claims," or "is this supported by the sources?"
What I need from you:
- The answer — the paragraph, bullet list, or report you want verified.
- The evidence — the sources it was based on. One of these forms:
- Copy-pasted text from the sources, OR
- URLs (I'll note which claims reference which URL but can't fetch them if I don't have browsing), OR
- A structured list like
[1] <source text>,[2] <source text>.
If you only paste the answer without evidence, I'll ask what sources you want it checked against.
How I verify
For every answer, I run this protocol:
- Decompose — I extract each standalone factual claim as one line. A claim is something like "Paxlovid reduced hospitalization by 44 %" — a specific, checkable statement. I ignore editorial hedging, conclusions, and meta-sentences.
- Check — For each claim, I look through the evidence and mark it:
VERIFIED— the claim is directly supported by the evidence.UNVERIFIED— the evidence doesn't mention this claim (not wrong, just unsupported).CONTRADICTED— the evidence explicitly says something different from the claim.
- Report — Each claim on its own line with its verdict and a one-sentence justification referencing the evidence number.
- Summary —
X/Y claims verified+ the ratio + any red flags.
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 · 179 lines · 66 tokens per session scan A 6242ffa5e2ce
verify-answer is a skill published in the GitHub repository TheAiSingularity/agentic-research-engine-oss (1 stars, last pushed 4mo ago), licensed MIT. It adds 66 tokens to every session and 1,720 once invoked, about $0.0003 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
commit
Create a git commit for this repo ONLY after the full quality gate passes — format, lint, typecheck, tests, and build for everything the change touches (plus container integration tests when DB/queue code changed and Docker is up), and docs updated to match. Use whenever the user asks to commit, or before…
fable-method
A 7-step problem-solving discipline loop that gives any model structured thinking: classify the ask, define done, gather evidence, decide, act surgically, verify by observation, report outcome-first. Use when the user says 'fable-method', or proactively when starting any multi-step task that no task-specific skill…
fable-judge
Adversarial verification of finished work. Treats any 'done' claim as a set of claims to verify by re-running everything yourself. Use when someone reports work complete and you must gate it: load this before trusting a completion report. Subcommands: suite runs a trap suite against any skill/model.
audit-plan
Audit a design plan or proposal before any of it is built — decide for each capability whether it is the library's problem or the user's, and if the user's, whether they have the primitives to solve it; enumerate the permanent public surface it would add; verify every load-bearing claim against the real codebase…
fable-loop
The orchestrated version of fable-method: runs the same decide-act-verify-report loop but fans out parallel evidence subagents in planning and adversarial attacker subagents in verification. Four stages - PLAN, EXECUTE, VERIFY, AUDIT/REPORT - with a decision gate after the plan and a hard 3-cycle bound on failed…
fable-domain
Use when extending the fable-method problem-solving loop into a non-code domain (marketing, research, data analysis, ops). Generates a domain adapter bundle: workflow+flowchart, adapter, trap fixture, smoke eval. Refuses licensed/harm-causing domains, stops when no adapter is needed, and verifies its own output before…