Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Implement

ASecurity

Executes an approved plan directly in Codex with one primary implementation stream by default, bounded sidecars only when write scopes are truly disjoint, and mandatory review gates for completeness and intent fidelity. Use after a plan is approved.

477 stars
0 votes
0 copies
0 views
Added 9/22/2026
ai-agentsbashsqlgitfrontendbackend

Security Analysis

A100/100

Scanned 9/22/2026

Install to Claude Code

$npx -y skills add greenfield-inc/Pane --skill implement --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Implement?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Implement
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/greenfield-inc-implement-pane/badge)](https://www.skillsdirectory.com/skills/greenfield-inc-implement-pane)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: implement
description: Executes an approved plan directly in Codex with one primary implementation stream by default, bounded sidecars only when write scopes are truly disjoint, and mandatory review gates for completeness and intent fidelity. Use after a plan is approved.
argument-hint: "[plan file path]"
---

# Implement

Execute the approved plan directly in this Codex session.

Codex is the primary implementation authority in this workflow. If you also
have a separate Claude workflow available, treat it as an optional parallel
second-opinion lane rather than the primary executor.

## Step 1: Load Plan and Supporting Artifacts

- If a path is provided, read that plan
- If no path is provided, use the most recent file in `./tmp/ready-plans/`
- If the plan includes `Source Artifacts`, read the brief / intent artifact and
  research dossier before coding

Treat sources of truth as:
- Brief / intent artifact: why this work exists and what must not be optimized away
- Plan: execution shape, task ordering, and file-level implementation details
- Dossier: supporting evidence, patterns, and anchors

If no separate brief exists, treat the plan's `Intent / Why`, `Locked
Decisions`, `Known Mismatches / Assumptions`, and success criteria as the
minimum intent source of truth.

## Step 2: Identify Dangerous Commands

Before implementing, scan the plan for commands that must not be run
automatically:
- environment variable changes
- package installations that change manifests
- destructive or irreversible commands

Collect them into a `Manual Steps` list and surface them before proceeding.

Schema / migration handling is done later after review. Do not handle it here.

## Step 3: Choose Execution Strategy

Default to one primary implementation stream.

Only split work when all of the following are true:
- write scopes are genuinely disjoint
- the integration contract is already clear in the plan
- parallelism will not hide missing last-mile wiring
- one primary owner still handles final integration and finish-line checks

Keep these with the primary stream unless there is an unusually clean reason
not to:
- schema and shared types
- routing / bootstrap / exports
- auth / permissions / tokens
- jobs / async orchestration / dispatch semantics
- final frontend-to-backend wiring

## Step 4: Implement

- Read the full plan before editing code
- Read the supporting brief before coding when available
- Prefer existing patterns over new abstractions
- Prefer editing existing files over creating new ones
- Update the plan progress as work completes
- Do not silently simplify, defer, or narrow scope
- If you must deviate, add a short `Plan Delta` note to the plan
- A task is not complete until the end-to-end runtime or user-facing path is
  actually wired and still preserves the intended outcome

Run these quality checks during the work when feasible:

```bash
npm run typecheck
npm run lint
```

## Step 5: Review Gates

After implementation, always run a review pass against the standards in
`implementation-reviewer`.

Minimum gate:
- one full implementation review pass

Preferred gate:
- a fresh skeptical second-opinion pass in a separate context

If you are operating alongside a separate Claude workflow, you may use that
second lane in parallel. If not, perform an additional adversarial Codex review
focused on:
- missing plan tasks
- brief-intent regressions
- runtime wiring
- auth / permission gaps
- transaction boundaries
- race conditions
- background-job registration
- dead query-param flows
- whether the implementation actually reached the finish line

Do not surface questions until all active review lanes are complete and their
findings are merged.

Split findings into:
- Auto-fixable
- Needs user input

Apply straightforward fixes directly, then rerun the review gate when needed.

## Step 5.5: Generate Dev Migration SQL (If Schema Changed)

After review gates are complete and auto-fixable issues are resolved, check if
`schema.ts` was modified:

```bash
git diff origin/main --name-only | grep schema.ts
```

If schema changed:
1. Run `npm run db:diff:dev`
2. Present the generated SQL in a transaction block
3. Present the command to apply the dev migration
4. If destructive SQL appears, stop and ask the user before proceeding

If schema did not change, skip this step silently.

## Step 6: Move Plan to Done

Once all tasks pass review, brief intent is preserved, and the implementation is
complete, move the plan from `./tmp/ready-plans/` to `./tmp/done-plans/`.

Only move the plan when all tasks are confirmed complete.

## Step 7: Present Results

Present the final result with:
- quality checks and their status
- intent fidelity status
- completeness against the plan
- issues found
- questions needing user input
- manual steps remaining
- schema changes, if any
- final plan path if it was moved

If the review found issues, offer to fix them before the user commits.

Attribution

greenfield-incgreenfield-inc
View sourceMore from greenfield-inc →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1066601 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →