implement

A command for carrying out a previously written implementation plan one phase at a time. It checks the repository, reviews the plan, makes the changes, and verifies each phase.

In plain words
What is it for?
Use it when you have a plan document with phases, tasks, success criteria, and testing instructions to follow.
Why use it?
It gives planned work a structured execution process and helps catch problems through baseline checks and repeated verification.

Command for Claude Code

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.

agentmods
npx agentmods add commands/dgunning/edgartools/implement
Clone the repo
git clone --depth 1 https://github.com/dgunning/edgartools

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,522 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.01522
Opus 5 $0.00000 $0.00761
Sonnet 5 $0.00000 $0.00304
Haiku 4.5 $0.00000 $0.00152

Measured yesterday against content hash cc18150c00b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

implement 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • implement — 100% identical, 0 lines differ
.claude/commands/implement.md · 257 lines

How it starts

The opening of the file, as written. The whole thing — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implement Plan

You are tasked with implementing a plan step-by-step, following the phases outlined in the planning document. This is Phase 3 of the Frequent Intentional Compaction (FIC) workflow.

Initial Setup:

When this command is invoked, respond with:

🚀 Starting implementation (Phase 3 of FIC workflow)

I'll implement the plan phase by phase, verifying each step before proceeding.

Please provide the path to your implementation plan from Phase 2.

Implementation Process:

1. Load and Review Plan

  • Read the entire plan document
  • Identify all phases and their checkboxes (⬜)
  • Note which phases are already complete (✅)
  • Create a TodoWrite list matching the plan phases
  • Understand success criteria and verification steps

2. Pre-Implementation Checks

# Ensure clean working state
git status
git diff

# Run existing tests to ensure baseline
python -m pytest

# Check current branch
git branch --show-current

If not on a feature branch, suggest creating one:

git checkout -b feature/{description}

3. Phase-by-Phase Implementation

For each phase marked ⬜ in the plan:

A. Start Phase
  1. Update plan to mark phase as in-progress:
    • Change ### Phase N: [Name] ⬜ to ### Phase N: [Name] 🔄
  2. Update TodoWrite to mark phase as in_progress
  3. Announce what you're implementing
B. Implement Changes
  • Follow the plan's specified changes exactly
  • Use the Edit or MultiEdit tool for modifications
  • Create new files with Write when needed
  • Implement in the order specified in the plan
C. Verify Implementation

Run the verification steps from the plan:

# Run specific tests
python -m pytest tests/test_module.py::TestClass -xvs

# Check functionality
python -c "from edgar import Module; Module().test_new_feature()"

# Verify no regressions
python -m pytest tests/ -x
D. Handle Issues

If verification fails:

  1. Stop and analyze the discrepancy
  2. Document the issue:
    ⚠️ Issue in Phase N:
    Expected: [what plan said]
    Found: [actual situation]
    Attempting fix: [your solution]
    
  3. Fix and re-verify
  4. If unable to fix, ask user for guidance

Read the full file on GitHub · 257 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. yesterday First seen · 257 lines · 0 tokens per session scan A cc18150c00b6

Subscribe to this mod's changes

implement is a command published in the GitHub repository dgunning/edgartools (2,635 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,522 tokens. 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 2026-08-30.