chain-of-verification

chain-of-verification is a skill for Claude Code from nguyenthienthanh/aura-frog. It costs 51 tokens per session (1,319 once invoked), scanned A, original, MIT.

A checking process in which an agent drafts an answer, creates questions that could disprove it, verifies those questions with tools, and revises the answer. It is designed to reduce made-up facts in reports and reviews.

In plain words
What is it for?
Use it for reports, reviews, and other outputs that contain factual claims requiring verification.
Why use it?
It adds an independent fact-checking pass instead of trusting the first draft. This is especially relevant when making security or test claims.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is Human-readable explanation: see [docs/architecture/HIERARCHICAL_PLANNING.md](../../../docs/architecture/HIERARCHICAL_PLANNING.md).

Part of the aura-frog plugin — 43 skills, 24 commands, 15 agents, 10 hooks, 6 MCP servers shipped together

Good fit Use it for reports, reviews, and other outputs that contain factual claims requiring verification.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/nguyenthienthanh/aura-frog
agentmods
npx agentmods add skills/nguyenthienthanh/aura-frog/chain-of-verification

Made for: Claude Code.

Or install aura-frog, the plugin that ships this one along with the rest of its 43 skills, 24 commands, 15 agents, 10 hooks, 6 MCP servers.

Wrote 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.

agentmods badge for chain-of-verification

README.md
[![agentmods](https://agentmods.dev/badge/skills/nguyenthienthanh/aura-frog/chain-of-verification/github.svg)](https://agentmods.dev/skills/nguyenthienthanh/aura-frog/chain-of-verification)
Your own site
<a href="https://agentmods.dev/skills/nguyenthienthanh/aura-frog/chain-of-verification"><img src="https://agentmods.dev/badge/skills/nguyenthienthanh/aura-frog/chain-of-verification/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.

agentmods 80×15 button for chain-of-verification

Your own site · 80×15
<a href="https://agentmods.dev/skills/nguyenthienthanh/aura-frog/chain-of-verification"><img src="https://agentmods.dev/badge/skills/nguyenthienthanh/aura-frog/chain-of-verification.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,319 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Agent Snooping · line 150
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Agent Snooping · line 151
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00051 $0.01319
Opus 5 $0.00026 $0.00660
Sonnet 5 $0.00010 $0.00264
Haiku 4.5 $0.00005 $0.00132

Measured 12d ago against content hash 5c9631026b01, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

chain-of-verification 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 12d 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.

aura-frog/skills/chain-of-verification/SKILL.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI-consumed reference. Optimized for Claude to read during execution. Human-readable explanation: see docs/architecture/HIERARCHICAL_PLANNING.md or docs/getting-started/ depending on topic.

Chain-of-Verification

Catch hallucinations by forcing the model to verify its own claims via tools.

Governed by: rules/workflow/chain-of-verification.md (when / why — MANDATORY in Phase 4)


When NOT to Use

  • Simple file-list reports with no factual claims
  • Quick fixes that don't produce any claim
  • User uses just do: (but still verify destructive claims)
  • Already ran CoVe on this exact content (cache in memory)

The 4-Step Protocol

Step 1 — Draft

Generate the answer/report as normal. Do NOT optimize for correctness yet.

Step 2 — Plan verifications

List 3–5 focused questions that would disprove the draft. Each question must be:

  • Answerable via tool (Read/Bash/Grep/Glob) — not from memory
  • Independent — doesn't assume the draft is correct
  • Specific — targets a concrete claim, not a vibe

Step 3 — Execute verifications

For each question, run the tool and record the actual result. Don't reason about what "should" be — record what IS.

Step 4 — Revise

Compare each claim in the draft against verification results:

  • Claim verified → keep
  • Claim contradicted → fix
  • Claim unverifiable → soften ("appears to…" or remove)

Example — Phase 4 Security Review

Draft

Security review of /api/users endpoint:
- ✓ No SQL injection risks (uses parameterized queries)
- ✓ Rate-limited at 100 req/min
- ✓ Input validated before DB write
- ⚠ Password comparison timing-safe

Plan Verifications

Q1: Does src/api/users/route.ts use parameterized queries?
    → grep "raw\|concat" src/api/users/

Q2: Is there a rate-limit middleware on /api/users?
    → grep "rateLimit\|rate-limiter" src/api/users/ src/middleware/

Q3: Is input validated before any DB call?
    → Read src/api/users/route.ts — check order of validation vs DB call

Q4: Does password comparison use timing-safe function?
    → grep "timingSafeEqual\|bcrypt.compare" src/

Q5: What's the actual rate limit value?
    → grep -A 3 "rateLimit" src/middleware/

Read the full file on GitHub · 152 lines

Changes

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.

  1. 12d ago First seen · 152 lines · 51 tokens per session scan A 5c9631026b01

Subscribe to this mod's changes

chain-of-verification is a skill published in the GitHub repository nguyenthienthanh/aura-frog (24 stars, last pushed 8d ago), licensed MIT. It adds 51 tokens to every session and 1,319 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 2026-08-30.

Related

Other skills, from other repositories

openspec-plus-apply

MANDATORY skill that activates whenever the OpenSpec apply phase begins. Triggers: /opsx-apply runs, the openspec-apply-change vanilla skill is referenced or active, openspec instructions apply is invoked, or the user asks to implement, apply, execute, or build out an OpenSpec change ('implement the change', 'apply…

sudokar/openspec-plus · 110 tokens

openspec-plus-spec

MANDATORY skill that activates whenever the OpenSpec specification phase begins. Triggers: /opsx-new or /opsx-continue runs; openspec-new-change, openspec-continue-change, or openspec-explore is active; openspec instructions spec or openspec instructions specs is invoked; or the user wants to create, update, review…

sudokar/openspec-plus · 88 tokens

openspec-plus-tdd

MANDATORY skill that activates whenever code is written to implement an OpenSpec change task. Triggers: openspec-plus-apply is active, /opsx-apply is running, the user is implementing tasks from an OpenSpec change, an implementer subagent dispatched by openspec-plus-apply is starting work, or the user invokes phrases…

sudokar/openspec-plus · 190 tokens

openspec-plus-proposal

MANDATORY skill that activates whenever the OpenSpec proposal phase begins. Triggers: /opsx-new or /opsx-continue runs; openspec-new-change, openspec-continue-change, or openspec-explore is active; openspec instructions proposal is invoked; or the user wants to create, update, review, refine, or discuss an OpenSpec…

sudokar/openspec-plus · 82 tokens

openspec-plus-tasks

MANDATORY skill that activates whenever the OpenSpec tasks phase begins. Triggers: /opsx-new or /opsx-continue runs; openspec-new-change, openspec-continue-change, or openspec-explore is active; openspec instructions tasks is invoked; or the user wants to create, update, review, refine, or discuss an OpenSpec tasks.md…

sudokar/openspec-plus · 84 tokens

implement-type-annotations

Add comprehensive type hints to Python/TypeScript code to improve IDE support, catch errors early, and enable better AI code understanding.

ambient-code/agentready · 30 tokens