verify-finalize

A script-driven final step for verification runs that uploads visual evidence to Linear and posts the verification summary together.

In plain words
What is it for?
It helps finalize complete or blocked verification runs using a manifest of test items and evidence.
Why use it?
It prevents verification from finishing with screenshots that were captured but never attached to the issue.

Skill for Claude CodeCodex

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/implicit-labs/autosymph/verify-finalize
Any agent
npx skills add implicit-labs/autosymph --skill verify-finalize
Clone the repo
git clone --depth 1 https://github.com/implicit-labs/autosymph

Made for: Claude Code, Codex.

Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,371 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00069 $0.01371
Opus 5 $0.00034 $0.00685
Sonnet 5 $0.00014 $0.00274
Haiku 4.5 $0.00007 $0.00137

Measured 2d ago against content hash c963b882e53d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

verify-finalize scanned grade A with 1 finding 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 2d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/verify-finalize.sh, test.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

parsing + table-building without hitting real Linear (curl is PATH-stubbed
skills/verify-finalize/SKILL.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

verify-finalize

The verify agent's ONLY end-action. Build a manifest, call this script. Done.

Why this skill exists

verify-completion-audit gives deterministic detection of "the agent took screenshots and uploaded none." Detection alone is not enough: prompt-only enforcement can still be skipped during a long verify run.

This skill replaces the discipline rule with a mechanical can't-skip-it: the agent's only end-action is calling verify-finalize.sh. The script handles upload + post atomically. The agent CAN'T forget — there's no separate sub-step to forget.

When to use

Always, as the LAST tool call of every verify run. Replaces:

  • All direct mcp__linear__create_attachment calls
  • The single mcp__linear__save_comment call with the summary table

If preflight (Phase 0) blocked verify before iOS work, you still call verify-finalize with the BLOCKED-marked items. There's never a verify run that should NOT end with verify-finalize.

Manifest schema

JSON file. Required fields: issue_id, session_name, result, items. Optional: minor_fixes_applied.

{
  "issue_id": "ISSUE-123",
  "session_name": "ISSUE-123-verify-run14",
  "result": "complete",
  "minor_fixes_applied": "none",
  "items": [
    {
      "n": 1,
      "item": "swift build passes",
      "method": "cli",
      "status": "PASS",
      "evidence": "exit code 0"
    },
    {
      "n": 6,
      "item": "Header in Text mode",
      "method": "ios-simulator + video",
      "status": "PASS",
      "evidence_path": "<workspace>/verify-1.mp4",
      "evidence_kind": "video"
    },
    {
      "n": 12,
      "item": "Dynamic Type largest size",
      "method": "screenshot",
      "status": "PASS",
      "evidence_path": "<workspace>/verify-2.png",
      "evidence_kind": "image"
    },
    {
      "n": 8,
      "item": "iOS chrome",
      "method": "ios-simulator + video",
      "status": "BLOCKED",
      "evidence": "preflight: idb broken (pyexpat ImportError)"
    },
    {
      "n": 16,
      "item": "Aesthetic match vs design ref",
      "method": "human",
      "status": "SKIPPED: human-only"
    }
  ]
}

Read the full file on GitHub · 150 lines

Files

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.

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. 2d ago First seen · 150 lines · 69 tokens per session scan A c963b882e53d

Subscribe to this mod's changes

verify-finalize is a skill published in the GitHub repository implicit-labs/autosymph (5 stars, last pushed 8d ago), licensed MIT. It adds 69 tokens to every session and 1,371 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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

use-agent-browser-for-airi

Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…

moeru-ai/airi · 87 tokens

test-conversion

Workflow for converting unit tests to browser tests for Project Bedrock. Invoke this when the user wants to remove complex Browser dependencies from tests.

chromium/chromium · 31 tokens

agui-dotnet-cross-language-tests

Author cross-language interop tests that verify the AG-UI .NET SDK is wire-compatible with the TypeScript SDK — a Vitest TS client driving a C# CrossLanguage.TestServer over HTTP, both directions, including protobuf byte-parity against @ag-ui/proto. USE FOR: adding or modifying cross-language interop coverage…

ag-ui-protocol/ag-ui · 146 tokens

cli-e2e-testcase-writer

Use when adding or updating Go CLI E2E coverage for one tests/clie2e/{domain} domain of the compiled lark-cli, especially when the work requires live --help or schema exploration, scenario-based clie2e.RunCmd workflows, and per-domain coverage.md maintenance.

larksuite/cli · 78 tokens

harness-test-writer

Add regression test cases to the Bifrost provider harness (the Postman collection run via make run-provider-harness-test) based on a merged PR or a GitHub issue. Fetches the PR/issue, traces the affected wire path in the codebase, checks existing harness coverage, designs cases following harness conventions, inserts…

maximhq/bifrost · 133 tokens

develop-web-game

Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with rendergametotext.

netease-youdao/LobsterAI · 64 tokens