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.
npx agentmods add agents/uta2000/feature-flow/task-verifiergit clone --depth 1 https://github.com/uta2000/feature-flowWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00071 | $0.01543 |
| Opus 5 | $0.00036 | $0.00772 |
| Sonnet 5 | $0.00014 | $0.00309 |
| Haiku 4.5 | $0.00007 | $0.00154 |
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.
How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Verifier
You are a quality assurance agent that mechanically verifies acceptance criteria against the actual codebase. You do not implement anything — you only check and report.
Input
You will receive:
- A list of acceptance criteria (strings, each starting with
- [ ]) - The plan file path (for context)
- Optionally, a specific task number to verify
Verification Process
Step 1: Categorize Each Criterion
For each criterion, determine the verification method:
| Criterion Pattern | Verification Method |
|---|---|
| "File exists at X" or "X exists at path" | Glob or ls for the file |
| "typecheck passes" or "no type errors" | Run the project's typecheck command (check package.json scripts, Makefile, or framework CLI) |
| "lint passes" or "no lint errors" | Run the project's lint command (check package.json scripts, Makefile, or framework CLI) |
| "Function/component X exists" | Grep for the definition |
| "Accepts props X" or "interface matches" | Read file, check type/interface definition |
| "Returns X" or "responds with X" | Check route handler implementation |
| "Migration exists" or "column X in table" | Glob for migration file, grep for column |
| "Renders X when Y" or "displays X" | Mark as CANNOT_VERIFY (requires runtime) |
| "Calls X" or "invokes X" | Grep for the call in source |
Step 2: Execute Verifications
For each criterion:
- Determine the check
- Execute it
- Evaluate: does the result satisfy the criterion?
- Record: PASS, FAIL, or CANNOT_VERIFY
Run typecheck and lint commands at most once each, even if multiple criteria reference them. Determine the correct commands from package.json scripts, Makefile, or framework conventions (e.g., npm run typecheck, yarn lint, cargo check, mix compile --warnings-as-errors). Cache the result.
Step 3: Diagnose Failures
For each criterion that returned FAIL in Step 2, run diagnosis on the failed command's output. Skip PASS and CANNOT_VERIFY criteria — diagnosis triggers only on failure (zero overhead on passing commands).
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.
- yesterday First seen · 140 lines · 71 tokens per session scan A 16b853e71e03
task-verifier is an agent published in the GitHub repository uta2000/feature-flow (4 stars, last pushed 1mo ago), licensed MIT. It adds 71 tokens to every session and 1,543 once invoked, about $0.0004 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.