twining-verify

twining-verify is a skill for Claude Code, Codex from daveangulo/twining-mcp. It costs 39 tokens per session (844 once invoked), scanned A, original, MIT.

A pre-completion check for complex coding work. It reviews warnings, recorded decisions, supporting tests, gathered context, constraints, and possible drift from the original intent.

In plain words
What is it for?
Checking multi-file changes, architectural decisions, large tasks, or pull requests. Simple tasks can instead receive a status update through twining_post.
Why use it?
It helps find unresolved issues or changes that no longer match earlier decisions before work is handed off or submitted.

Skill for Claude CodeCodex

Part of the twining plugin — 9 skills, 2 commands, 2 agents, 5 hooks shipped together

Install

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.

agentmods
npx agentmods add skills/daveangulo/twining-mcp/twining-verify
Any agent
npx skills add daveangulo/twining-mcp --skill twining-verify
Clone the repo
git clone --depth 1 https://github.com/daveangulo/twining-mcp

Made for: Claude Code, Codex.

Or install twining, the plugin that ships this one along with the rest of its 9 skills, 2 commands, 2 agents, 5 hooks.

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 twining-verify

README.md
[![agentmods](https://agentmods.dev/badge/skills/daveangulo/twining-mcp/twining-verify.svg)](https://agentmods.dev/skills/daveangulo/twining-mcp/twining-verify)
Your own site
<a href="https://agentmods.dev/skills/daveangulo/twining-mcp/twining-verify"><img src="https://agentmods.dev/badge/skills/daveangulo/twining-mcp/twining-verify.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 844 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00039 $0.00844
Opus 5 $0.00019 $0.00422
Sonnet 5 $0.00008 $0.00169
Haiku 4.5 $0.00004 $0.00084

Measured 5d ago against content hash f797e36ffc3b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

twining-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 5d 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.

plugin/skills/twining-verify/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Twining Verify — Pre-Completion Verification

For complex tasks (multi-file changes, architectural decisions, long sessions), verify your work against Twining's coordination state. For simple tasks, posting a status entry via twining_post is sufficient.

Note: twining_verify requires tools.full_surface: true in config. If not available, post a status entry via twining_post summarizing what you did.

When to Invoke

  • Complex multi-file changes with architectural decisions
  • Before handing off work to another agent on a large task
  • Before creating a pull request with significant changes
  • When you want to check for decision drift or unresolved warnings

Workflow

1. Run Verification

Call twining_verify with:

  • scope: The area you worked on (e.g., "src/auth/")
  • checks: Array of checks to run. Include all relevant ones:
    • "test_coverage" — Are decisions backed by tested_by relations?
    • "warnings" — Are all warnings acknowledged or resolved?
    • "assembly" — Were decisions made after assembling context (not "blind")?
    • "drift" — Has code drifted from decision intent?
    • "constraints" — Do checkable constraints still pass?

2. Interpret Results

Each check returns a status:

pass — No issues found. Proceed.

warn — Issues exist but aren't blocking:

  • Uncovered decisions (no tested_by relation) — consider adding test links
  • Blind decisions (made without twining_assemble) — acknowledge or re-verify
  • Minor drift detected — review if decisions are still accurate

fail — Issues that should be addressed:

  • Silently ignored warnings — read and acknowledge each one
  • Failed constraint checks — fix the violation or update the constraint
  • High drift count — decisions may be stale

3. Address Issues

For each issue found:

Uncovered decisions — If you wrote tests that cover a decision and the knowledge graph is enabled (graph.auto_populate: true), link them:

twining_add_relation(
  source="<affected_file>",
  target="<test_file>",
  type="tested_by",
  properties={ covers: "<what it tests>" }
)

If the graph is not enabled, this check can be safely ignored.

Read the full file on GitHub · 94 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. 5d ago First seen · 94 lines · 39 tokens per session scan A f797e36ffc3b

Subscribe to this mod's changes

twining-verify is a skill published in the GitHub repository daveangulo/twining-mcp (7 stars, last pushed 9d ago), licensed MIT. It adds 39 tokens to every session and 844 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

potpie-infra-architecture

Use for project infra and architecture context: environments, adapters, runtime configuration, deployments, service dependencies, datastores, API contracts, ownership, incidents, and dependency blast radius.

potpie-ai/potpie · 43 tokens

alfworld-search-pattern-executor

Systematically searches a sequence of likely locations for a target object based on common sense. Use when you need to find a specific object and know which receptacles to check but not which one contains it. Takes a list of candidate receptacles, orchestrates navigation and inspection, and outputs when the target is…

zjunlp/SkillNet · 74 tokens

task-planning-arch

计算任务 gap 并产出下一步可执行子任务 List[TaskSpec];gap 已闭返回空数组。对齐 arch 场景(架构师名册/技术栈概览/双视角分析)确定式分解——按根目标交付物集合 + donechildren 查表(参照 task-planning storage 特例,非自由 LLM 分解)。.

inclusionAI/Avernet · 89 tokens

task-search

在框架预查的候选 bot 集里决出执行者(who)与协作方式(how),返回 4 态 SearchResult(HITSINGLE/HITGROUP/HITMULTIBOTS/MISS)。对齐案例剧本确定式映射。.

inclusionAI/Avernet · 59 tokens

scienceworld-growth-focuser

Use when you have planted a seed or need to track a plant's growth stage (sprouting, flowering, reproduction). Applies the 'focus on' action to a specific plant or biological entity to signal intent and monitor its development. Trigger after planting or when you need to observe life cycle progression in the…

zjunlp/SkillNet · 71 tokens

scienceworld-tool-user

Uses a tool from inventory on a target object or location to perform a specific environmental interaction, such as digging, cutting, or measuring. Use this skill when a task requires modifying the environment or manipulating materials with a tool (e.g., using a shovel to dig soil, a thermometer to measure temperature…

zjunlp/SkillNet · 87 tokens