Borrowing it
Nothing to install: this file belongs to jongwony/epistemic-protocols. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jongwony/epistemic-protocols/main/.claude/skills/verify/SKILL.mdgit clone --depth 1 https://github.com/jongwony/epistemic-protocolsWrote 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/jongwony/epistemic-protocols/verify)<a href="https://agentmods.dev/skills/jongwony/epistemic-protocols/verify"><img src="https://agentmods.dev/badge/skills/jongwony/epistemic-protocols/verify/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/jongwony/epistemic-protocols/verify"><img src="https://agentmods.dev/badge/skills/jongwony/epistemic-protocols/verify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 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 163 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 166 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 167 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.
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 | $0.00058 | $0.01263 |
| Opus 5.5 | $0.00023 | $0.00505 |
| Sonnet 5.5 | $0.00012 | $0.00253 |
| Haiku 4.5 | $0.00006 | $0.00126 |
Grade A, and why
verify 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 9d 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Protocol Verification
Verify epistemic protocol consistency before commit through static checks and expert review.
Purpose
Surface potential issues in protocol definitions without blocking commits. Follow Anthropic philosophy: transparency over enforcement, user agency over automation.
Core Principles
| Principle | Implementation |
|---|---|
| Surface, don't enforce | Present findings; user decides action |
| Zero-context scripts | Static checks run without consuming context |
| Explicit control | User invokes /verify intentionally |
| Graduated severity | Critical / Concern / Note categorization |
Workflow
Phase 1: Static Checks
Run scripts/static-checks.js against project root. This script executes without loading into context.
node ${SKILL_DIR}/scripts/static-checks.js ${PROJECT_ROOT}
Output format:
{
"pass": [{ "check": "...", "file": "...", "message": "..." }],
"fail": [{ "check": "...", "file": "...", "message": "..." }],
"warn": [{ "check": "...", "file": "...", "message": "..." }]
}
Checks performed: scripts/static-checks.js is the orchestrator. Its head names the layer files it runs and what each layer holds, and each layer file's CHECKS list is that layer's inventory. references/verification.md carries why the non-obvious checks exist and what to do when one fires.
Phase 2: Expert Review
Spawn parallel Task subagents for LLM-based review — one per perspective (Type Theory / Category Theory, Instruction Design, Claude Code Ecosystem). Load each subagent's prompt template from references/review-checklists.md (single source of truth; do not duplicate the templates here — see Review Checklists below). Each template samples the protocols changed in the current diff, falling back to a representative sample when the diff is not protocol-scoped.
All three subagents run in parallel. Collect results before proceeding.
Phase 3: Synthesize Findings
What ships with it
13 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.
- references/co-change.md 17 KB
- references/criteria.md 5.9 KB
- references/review-checklists.md 8.0 KB
- references/verification.md 10 KB
- scripts/artifact-self-containment.js 9.3 KB runs code
- scripts/artifact-sync.js 52 KB runs code
- scripts/check-context.js 4.3 KB runs code
- scripts/language-purity.js 4.0 KB runs code
- scripts/lean-bridge.js 19 KB runs code
- scripts/lean-contract.js 13 KB runs code
- scripts/prose-surface.js 12 KB runs code
- scripts/static-checks.js 1.2 KB runs code
- scripts/static-checks.test.mjs 34 KB runs code
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.
- 9d ago Changed 64d0c94a88d5
- 19d ago Changed 887143362767
- 26d ago Changed f1da17247300
- 28d ago Changed · -4 lines 9e90b1301020
- 29d ago Changed 306da644a20e
- 1mo ago Changed bf520539d684
- 1mo ago Changed · -4 lines 667ab6fe3c21
- 1mo ago First seen · 179 lines · 58 tokens per session scan A af4725de0901
verify is a skill published in the GitHub repository jongwony/epistemic-protocols (174 stars, last pushed yesterday), licensed MIT. It adds 58 tokens to every session and 1,263 once invoked, about $0.0002 per session on Opus 5.5. 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
flow-next-tracker-sync
Project a flow-next spec to a tracker issue (Linear, GitHub, GitLab, Jira) and reconcile two-way. Use when asked to sync to a tracker. NOT plan-sync.
flow-next-resolve-pr
Resolve PR review feedback. Fetches unresolved threads, triages, fixes, replies and resolves via GraphQL. Use when asked to address review comments.
taiyi-ui-design
A design-planning guide for describing how an application's user interface should look and behave. It produces a UI-DESIGN.md document covering layouts, components, interactions, accessibility, and error states.
plugin-code-review-orchestrated
Orchestrates a code review of the spring-plugin repository through scope/context passes, routing, domain reviewer subskills, and per-artifact validation. Use when asked to review a PR, diff, commit, branch, module, or file set, to run a full orchestrated review, or to produce a validated review report.
docs
Use when documentation generally needs to catch up with a branch before pushing or merging, covering internal developer docs, external customer-facing docs, and release notes together — "update the docs", "do a docs pass before I merge", "make sure everything's documented". Prefer this when no single documentation…
fix-js-globals
Fix JavaScript no-globals errors that UI5 linter reports but cannot auto-fix. Use this skill when linter outputs: no-globals rule with message "Access of global variable '...' (...)" in JS files Cases handled (linter CANNOT auto-fix): Assignments to global namespaces: sap.myNamespace = {...} Global namespace…