implement-spec

implement-spec is a skill for Claude Code from bacchus-labs/wrangler. It costs 22 tokens per session (4,012 once invoked), scanned A, original, MIT.

An end-to-end workflow for turning a software specification into an implemented GitHub pull request. A pull request is a proposed set of code changes for review.

In plain words
What is it for?
Use it when you want a specification implemented, verified, documented, and submitted as a pull request with execution records.
Why use it?
It organizes implementation into tracked sessions with isolated workspaces and an audit trail, making the work easier to review and recover.

Skill for Claude Code

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

Part of the wrangler plugin — 25 skills, 16 commands, 13 agents shipped together

Good fit Use it when you want a specification implemented, verified, documented, and submitted…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bacchus-labs/wrangler/implement-spec-vold
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.

Any agent
npx skills add bacchus-labs/wrangler --skill implement-spec-vold
Clone the repo
git clone --depth 1 https://github.com/bacchus-labs/wrangler

Made for: Claude Code.

Or install wrangler, the plugin that ships this one along with the rest of its 25 skills, 16 commands, 13 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 implement-spec

README.md
[![agentmods](https://agentmods.dev/badge/skills/bacchus-labs/wrangler/implement-spec-vold.svg)](https://agentmods.dev/skills/bacchus-labs/wrangler/implement-spec-vold)
Your own site
<a href="https://agentmods.dev/skills/bacchus-labs/wrangler/implement-spec-vold"><img src="https://agentmods.dev/badge/skills/bacchus-labs/wrangler/implement-spec-vold.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,012 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 $0.00022 $0.04012
Opus 5 $0.00011 $0.02006
Sonnet 5 $0.00004 $0.00802
Haiku 4.5 $0.00002 $0.00401

Measured 6d ago against content hash eae0bf49dbd7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

implement-spec 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 6d 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.

.wrangler/memory/knowledge-base/reference-prompts/skills/implement-spec-vOLD/SKILL.md · 709 lines

How it starts

The opening of the file, as written. The whole thing — 709 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implement-Spec Orchestrator

Skill Usage Announcement

MANDATORY: When using this skill, announce it at the start with:

Using Skill: implement-spec | [brief purpose based on context]

Example:

Using Skill: implement-spec | Implementing spec-auth-system.md with full audit trail

This creates an audit trail showing which skills were applied during the session.

Overview

End-to-end orchestration that takes a specification file and produces a GitHub Pull Request with comprehensive audit trail.

Core principle: Single command produces PR with verified implementation, full observability, and recovery capability.

Entry point: /wrangler:implement [spec-file]

Produces:

  • GitHub Pull Request with comprehensive summary
  • Audit trail in .wrangler/sessions/{session-id}/
  • Machine-verifiable execution log

When to Use

Use this skill when:

  • User says "implement this spec" and wants a PR
  • You want full audit trail and observability
  • You need session recovery capability
  • You want isolated worktree for implementation

Do NOT use this skill when:

  • Implementing a single issue (use implement skill directly)
  • User wants manual control over each step
  • Working on existing PR or branch (use implement skill)

Workflow Phases

The orchestrator executes 6 phases in order:

INIT -> PLAN -> EXECUTE -> VERIFY -> PUBLISH -> REPORT

Each phase is tracked via MCP session tools for full observability.

Phase 1: INIT

Initialize session, create worktree, and establish context.

Steps

  1. Start session

    Call session_start MCP tool:

    session_start(specFile: "{SPEC_FILE}")
    

    Capture response:

    • SESSION_ID = response.sessionId
    • WORKTREE_ABSOLUTE = response.worktreePath
    • BRANCH_NAME = response.branchName
    • AUDIT_PATH = response.auditPath
  2. Verify worktree

    cd {WORKTREE_ABSOLUTE} && \
      echo "=== WORKTREE VERIFICATION ===" && \
      echo "Directory: $(pwd)" && \
      echo "Git root: $(git rev-parse --show-toplevel)" && \
      echo "Branch: $(git branch --show-current)" && \
      test "$(git branch --show-current)" = "{BRANCH_NAME}" && echo "VERIFIED" || echo "FAILED"
    

Read the full file on GitHub · 709 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. 6d ago First seen · 709 lines · 22 tokens per session scan A eae0bf49dbd7

Subscribe to this mod's changes

implement-spec is a skill published in the GitHub repository bacchus-labs/wrangler (4 stars, last pushed 6mo ago), licensed MIT. It adds 22 tokens to every session and 4,012 once invoked, about $0.0001 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.