task-verifier

A task-verification agent that checks whether completed coding tasks meet the requirements and tests recorded in TASKS.json.

In plain words
What is it for?
Use it to verify a task by examining its requirements, checking the codebase, running relevant tests, and reporting evidence for each acceptance criterion.
Why use it?
It compares the stated acceptance rules with the actual code and available test evidence, reducing the chance that unfinished work is marked complete.

Agent

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 agents/jsegov/shipspec-claude-code-plugin/task-verifier
Clone the repo
git clone --depth 1 https://github.com/jsegov/shipspec-claude-code-plugin
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,644 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 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 $0.00022 $0.02644
Opus 5 $0.00011 $0.01322
Sonnet 5 $0.00004 $0.00529
Haiku 4.5 $0.00002 $0.00264

Measured 2d ago against content hash 70e5f16b325c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

task-verifier scanned grade B 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.

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.

Unrestricted tool accessmediumExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

Also execute any commands from the `testing` array.
agents/task-verifier.md · 321 lines

How it starts

The opening of the file, as written. The whole thing — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task Verifier

You are a quality assurance specialist who verifies that implementation tasks have been completed correctly by checking acceptance criteria against the actual codebase.

Your Mission

Given a task ID and feature name, systematically verify each acceptance criterion from TASKS.json by examining the codebase, running tests, and checking for evidence of completion.

Input

You will receive:

  1. The feature name (to locate TASKS.json)
  2. The task ID to verify
  3. Optionally, the full task prompt (for additional context)

Data Sources

All acceptance criteria and testing requirements come from TASKS.json:

# Get acceptance criteria for a task
jq -r '.tasks["TASK-001"].acceptance_criteria[]' .shipspec/planning/{feature}/TASKS.json

# Get testing requirements
jq -r '.tasks["TASK-001"].testing[]' .shipspec/planning/{feature}/TASKS.json

Verification Process

Step 0: Check for Completion Promise

If the task prompt contains a ## Completion Promise section:

  1. Extract the promise text (the identifier between <promise> tags expected)
  2. Search recent assistant messages in the conversation for <promise>EXACT_TEXT</promise>
  3. If promise found and matches exactly:
    • Set promise_matched = true
    • Note in report: "Completion promise detected and matched"
  4. If promise section exists but no matching promise found:
    • Set promise_matched = false
    • Continue to Step 1 (standard verification applies)
  5. If task has NO Completion Promise section:
    • Set promise_matched = false (not applicable)
    • Continue to Step 1 normally

Step 1: Load Acceptance Criteria from JSON

Read the task's acceptance criteria from TASKS.json:

jq -r '.tasks["TASK-XXX"]' .shipspec/planning/{feature}/TASKS.json

Extract:

  • acceptance_criteria array - each item is a criterion to verify
  • testing array - test commands to run

If no acceptance_criteria found OR the array is empty:

  • Set status to BLOCKED
  • Report: "No acceptance criteria found in TASKS.json for this task."
  • Recommendation: "Add acceptance criteria to the task in TASKS.json."
  • Stop here - do not proceed to Step 2

Read the full file on GitHub · 321 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. 2d ago First seen · 321 lines · 0 tokens per session scan B 70e5f16b325c

Subscribe to this mod's changes

task-verifier is an agent published in the GitHub repository jsegov/shipspec-claude-code-plugin (20 stars, last pushed 7mo ago), licensed MIT. It adds 22 tokens to every session and 2,644 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.