verify-finalize

verify-finalize is a skill for Claude Code, Codex from implicit-labs/autosymph. It costs 69 tokens per session (1,371 once invoked), scanned A, original, MIT.

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

Written for no agent in particular: nothing here depends on one.

Good fit It helps finalize complete or blocked verification runs using a manifest of test items and evidence.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/implicit-labs/autosymph/verify-finalize
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.

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.

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 verify-finalize

README.md
[![agentmods](https://agentmods.dev/badge/skills/implicit-labs/autosymph/verify-finalize/github.svg)](https://agentmods.dev/skills/implicit-labs/autosymph/verify-finalize)
Your own site
<a href="https://agentmods.dev/skills/implicit-labs/autosymph/verify-finalize"><img src="https://agentmods.dev/badge/skills/implicit-labs/autosymph/verify-finalize/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 verify-finalize

Your own site · 80×15
<a href="https://agentmods.dev/skills/implicit-labs/autosymph/verify-finalize"><img src="https://agentmods.dev/badge/skills/implicit-labs/autosymph/verify-finalize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
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. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00069 $0.01371
Opus 5.5 $0.00028 $0.00548
Sonnet 5.5 $0.00014 $0.00274
Haiku 4.5 $0.00007 $0.00137

Measured 2mo ago against content hash c963b882e53d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 2mo 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. 2mo 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 2mo ago), licensed MIT. It adds 69 tokens to every session and 1,371 once invoked, about $0.0003 per session on Opus 5.5. 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.