feature-verifier

feature-verifier is an agent for Claude Code from Jamie-BitFlight/claude_skills. It costs 49 tokens per session (4,338 once invoked), scanned A, original, MIT.

An agent that verifies whether an implemented feature delivers its expected outcomes by testing it from the user's perspective.

In plain words
What is it for?
Use it after implementation to verify that the feature exists, is wired into the project, and works toward its stated goal.
Why use it?
It checks the result rather than trusting completion claims or the mere presence of code. It reports concrete gaps when the feature is incomplete or not connected properly.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions subagents.

Part of the dh plugin — 53 skills, 28 agents shipped together

Good fit Use it after implementation to verify that the feature exists, is wired into the project, and works toward its stated goal.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/jamie-bitflight/claude_skills/feature-verifier
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.

Clone the repo
git clone --depth 1 https://github.com/Jamie-BitFlight/claude_skills

Made for: Claude Code.

Or install dh, the plugin that ships this one along with the rest of its 53 skills, 28 agents.

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 feature-verifier

README.md
[![agentmods](https://agentmods.dev/badge/agents/jamie-bitflight/claude_skills/feature-verifier.svg)](https://agentmods.dev/agents/jamie-bitflight/claude_skills/feature-verifier)
Your own site
<a href="https://agentmods.dev/agents/jamie-bitflight/claude_skills/feature-verifier"><img src="https://agentmods.dev/badge/agents/jamie-bitflight/claude_skills/feature-verifier.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,338 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00049 $0.04338
Opus 5 $0.00024 $0.02169
Sonnet 5 $0.00010 $0.00868
Haiku 4.5 $0.00005 $0.00434

Measured 3d ago against content hash 97c01902954b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

feature-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 3d 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.

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.

plugins/development-harness/agents/feature-verifier.md · 532 lines

How it starts

The opening of the file, as written. The whole thing — 532 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are spawned by:

  • Implementation completion workflows (after all tasks marked complete)
  • Direct Agent tool invocation for feature verification

Your job: Goal-backward verification. Start from what the feature SHOULD deliver, verify it actually exists and works.

Critical mindset: Do NOT trust task completion claims. Tasks document what Claude SAID it did. You verify what ACTUALLY exists and works. These often differ.

<complementary_verification>

Relationship to TN Verification Gate

This agent performs structural verification — it checks that goals were achieved, artifacts exist and are wired, and key links are connected.

The tn-verification-gate agent performs behavioral verification — it re-runs the plan's acceptance-criteria-structured commands and compares exit codes and stdout against the T0 baseline captured before implementation.

These two verification layers are complementary, not redundant:

  • Feature-verifier catches structural gaps (missing files, unwired imports, stub implementations, broken key links).
  • TN catches behavioral regressions (test commands that passed before implementation now fail).

A plan that passes feature-verifier but fails TN has structural correctness with behavioral regression. Both must pass for completion. /complete-implementation reads TN verdict before invoking this agent — if TN reports FAIL, this agent is not invoked.

</complementary_verification>

<core_principle> Task completion ≠ Goal achievement

A task "create runner config function" can be marked complete when the function is a placeholder. The task was done — a file was created — but the goal "working runner configuration" was not achieved.

Goal-backward verification starts from the outcome and works backwards:

  1. What must be TRUE for the goal to be achieved?
  2. What must EXIST for those truths to hold?
  3. What must be WIRED for those artifacts to function?

Then verify each level against the actual codebase. </core_principle>

<critical_rules>

DO NOT trust task completion claims. Tasks say "implemented function" — you verify the function works.

DO NOT assume existence = implementation. A file existing is level 1. You need level 2 (substantive) and level 3 (wired) verification.

DO NOT skip key link verification. This is where 80% of bugs hide. The pieces exist but aren't connected.

DO flag for human verification when uncertain. If you can't verify programmatically, say so explicitly.

DO keep verification fast. Use grep/file checks where possible. Goal is structural verification + key functional tests.

</critical_rules>

<verification_process>

Read the full file on GitHub · 532 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. 3d ago Changed 97c01902954b
  2. 4d ago First seen · 532 lines · 49 tokens per session scan A c64848a1a78c

Subscribe to this mod's changes

feature-verifier is an agent published in the GitHub repository Jamie-BitFlight/claude_skills (66 stars, last pushed today), licensed MIT. It adds 49 tokens to every session and 4,338 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 2026-09-03.

Related

Other agents, from other repositories

project-implementer

Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.

athola/claude-night-market · 38 tokens

sdd-init

Initialize project SDD context, testing capabilities, and skill registry.

Gentleman-Programming/gentle-pi · 17 tokens

python-pro

Write idiomatic Python code with advanced features like decorators, generators, and async/await. Optimizes performance, implements design patterns, and ensures comprehensive testing. Use PROACTIVELY for Python refactoring, optimization, or complex Python features.

echoVic/blade-code · 51 tokens

test-engineer

QA engineer operating on the "Prove-It" principle — if it works, prove it with a test. Use when writing tests for a new feature, filling coverage gaps, or validating that a bug fix won't regress. Can read, write and edit test files. Dispatch with Task tool for isolated test work.

felvieira/claude-skills-fv · 66 tokens

test-writer

Use this agent when the guild needs unit or integration tests written for implemented code. The test-writer implements the test-planner's test plan — reading the plan's Changed Files Inventory instead of re-analyzing the codebase — then writes and runs the tests. Spawned by the check-in skill when a test-writing task…

HirogaKatageri/hirokata · 77 tokens

implement-test-diversifier

Generates test suites from 4 different testing perspectives for comprehensive coverage.

eai-support/eai-gofer · 19 tokens