task-verifier

An AI-based checker that judges whether a completed coding task meets its acceptance criteria. It returns pass or fail with reasoning using a defined rubric.

In plain words
What is it for?
Use it to verify task bundles, required files, implementation evidence, and acceptance criteria after work is completed.
Why use it?
It checks the actual implementation against the requested outcome, not only whether automated tests run successfully.

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/dowwie/tasker/task-verifier
Clone the repo
git clone --depth 1 https://github.com/Dowwie/tasker
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,924 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 $0.00032 $0.01924
Opus 5 $0.00016 $0.00962
Sonnet 5 $0.00006 $0.00385
Haiku 4.5 $0.00003 $0.00192

Measured yesterday against content hash f42b4f44789e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

task-verifier 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 yesterday.

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.

agents/task-verifier.md · 262 lines

How it starts

The opening of the file, as written. The whole thing — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task Verifier (LLM-as-Judge)

Evaluate a completed task's implementation against acceptance criteria. You are a judge, not just a test runner.

Self-Completion Protocol: This verifier writes detailed results to bundles/{task_id}-verification.json. It returns ONLY PASS or FAIL to the executor. This minimizes executor context usage.

Input

You receive from task-executor:

Verify task T001

TASKER_DIR: {absolute path to .tasker directory}
Bundle: {TASKER_DIR}/bundles/T001-bundle.json
Target: /path/to/target/project

CRITICAL: Use the TASKER_DIR absolute path provided. Do NOT use relative paths.

Protocol

1. Load Context

cat {TASKER_DIR}/bundles/T001-bundle.json

Extract: name, behaviors, files, acceptance_criteria, constraints, task_type, state_machine (if present).

2. Gather Evidence

Mandatory Deliverables Check
TASK_ID="T001"
test -f "$TARGET_DIR/docs/${TASK_ID}-spec.md" && echo "SPEC EXISTS" || echo "SPEC MISSING"

If spec file is missing, verdict is FAIL.

Implementation Files

For each file in bundle.files:

test -f "$TARGET_DIR/path/to/file.py" && echo "EXISTS" || echo "MISSING"

For each acceptance_criteria[].verification command:

cd $TARGET_DIR && pytest tests/auth/test_validator.py -v 2>&1

3. Judge Against Rubric

Functional Correctness (Required)
Score Meaning
PASS Implementation meets the criterion
PARTIAL Partially implemented, missing edge cases
FAIL Does not meet criterion or broken
Code Quality (Required)
Dimension Check
Types Type annotations present and correct?
Docs Docstrings present and accurate?
Patterns Follows constraints.patterns?
Errors Error handling appropriate?
Test Quality (If tests exist)
Dimension Check
Coverage Tests cover the criterion?
Assertions Assertions meaningful?
Edge cases Edge cases tested?

Read the full file on GitHub · 262 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. yesterday First seen · 262 lines · 32 tokens per session scan A f42b4f44789e

Subscribe to this mod's changes

task-verifier is an agent published in the GitHub repository Dowwie/tasker (19 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 32 tokens to every session and 1,924 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 2026-08-30.