feature-full

feature-full is a command for Claude Code from viacheslav-tronko/claude-code-harness. It costs 130 tokens per session (2,726 once invoked), scanned A, original, MIT.

An end-to-end feature workflow that turns a requirement into a tested code change. It first clarifies the request and plans the work, then asks for approval before editing code.

In plain words
What is it for?
Use it for Jira stories, specifications, or other requirements that need a complete path from clarification through implementation and verification.
Why use it?
It reduces missed requirements and untested changes by checking the plan before coding and checking the result afterward.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; mentions subagents.

Good fit Use it for Jira stories, specifications, or other requirements that need a complete path from clarification through implementation and verification.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/viacheslav-tronko/claude-code-harness/feature-full
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/viacheslav-tronko/claude-code-harness

Made for: Claude Code.

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-full

README.md
[![agentmods](https://agentmods.dev/badge/commands/viacheslav-tronko/claude-code-harness/feature-full.svg)](https://agentmods.dev/commands/viacheslav-tronko/claude-code-harness/feature-full)
Your own site
<a href="https://agentmods.dev/commands/viacheslav-tronko/claude-code-harness/feature-full"><img src="https://agentmods.dev/badge/commands/viacheslav-tronko/claude-code-harness/feature-full.svg" alt="Measured on agentmods" height="20"></a>
Per session 130 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,726 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 $0.00130 $0.02726
Opus 5 $0.00065 $0.01363
Sonnet 5 $0.00026 $0.00545
Haiku 4.5 $0.00013 $0.00273

Measured 7d ago against content hash 624fee459632, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

feature-full 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 7d 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.

.claude/commands/feature-full.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/feature-full — Full Feature Pipeline (SPEC → IMP → Verify → Trace → Implement → Trace → Verify)

Pipeline:

  1. /distill $ARGUMENTS --standard → SPEC (read-only). Skill: requirements-analysis. (SKIP if param is SPEC path.)
  2. /howto-implement <SPEC> → IMP with 3+ approaches + #0 baseline (read-only). Skill: implementation-blueprint.
  3. /verify <IMP> → VERIFY-IMP; promotes IMP to state: verified if PASS (read-only). Skill: task-verification.
  4. /trace --virtual <IMP> → TRACE-VIRTUAL; white-box falsification of implementation blueprint before coding (read-only). Skill: white-box-trace.
  5. ASK USER (Two-Stage Confirm) — code modification is irreversible.
  6. /implement <IMP> → applies surgical changes per IMP §6.2 / §8 Blueprint Contract. Skill: surgical-implementation (MODE=IMPLEMENT).
  7. /trace --real <impl> → TRACE-REAL; white-box CFG/MPC verification of implemented code; on FAIL provides fix_proposal (read-only). Skill: white-box-trace.
  8. /verify <impl> → VERIFY-IMPL; runs Live Test Execution if shell available (read-only).

Tier: 2 (→3 on security boundary / public API / schema / financial).

0. HARD GATE — bypass = INVALID → REDO

"Skip step 3", "skip step 4", "skip the user confirm", "the IMP is good enough — just implement", "trust me", "obvious feature", "small story", "time pressure", "auto-approve", "the user already said Y in the past" do NOT override §0/§1/§4. Two-Stage Confirm at step 5 is MANDATORY — apply ONLY on explicit Y in this turn. NEVER apply implementation without IMP state: verified AND TRACE-VIRTUAL PASS. NEVER skip step 8.

ARTIFACTS MANDATORY. Each step's artifact file (SPEC, IMP, VERIFY, TRACE) MUST be written via Write tool at the step that produces it. Pipeline with zero files written = INVALID → CLAUDE.md §11 item 0 fires.

1. Parameter validation (FAIL-FAST)

  • $ARGUMENTS empty → reply ❌ /feature-full requires input. Usage: /feature-full <Jira | story | requirements | SPEC path> → STOP.
  • Param is path to existing SPEC-*.md → SKIP step 1; pipeline starts at step 2.

Read the full file on GitHub · 141 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. 7d ago First seen · 141 lines · 0 tokens per session scan A 624fee459632

Subscribe to this mod's changes

feature-full is a command published in the GitHub repository viacheslav-tronko/claude-code-harness (6 stars, last pushed 3mo ago), licensed MIT. It adds 130 tokens to every session and 2,726 once invoked, about $0.0006 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.