implement

A command for carrying out an existing implementation plan. It reads the plan, changes the listed files in order, and validates the work during the process.

In plain words
What is it for?
Use it when a plan file is ready to implement. It applies each task, runs syntax and test checks after changes, and stops if the plan or repository state is unsuitable.
Why use it?
It keeps implementation tied to the agreed tasks, coding patterns, acceptance criteria, and tests. It also checks the starting Git branch and working tree before making changes.

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/cognitx-leyton/codegraph/implement
Clone the repo
git clone --depth 1 https://github.com/cognitx-leyton/codegraph

Made for: Claude Code.

Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 614 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 $0.00007 $0.00614
Opus 5 $0.00003 $0.00307
Sonnet 5 $0.00001 $0.00123
Haiku 4.5 $0.00001 $0.00061

Measured yesterday against content hash 525462ccf912, 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.

.claude/commands/implement.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implement Plan (Step 4)

Plan: $ARGUMENTS

Phase 1: Load

Read the plan file and extract:

  • Tasks — ordered list of what to implement
  • Files to Change — CREATE/UPDATE list
  • Patterns to Mirror — code references to follow
  • Acceptance Criteria — what "done" looks like
  • Validation — how to verify

If plan not found:

Error: Plan not found at $ARGUMENTS
Create one first: /plan_local "feature description"

Phase 2: Verify Starting State

git branch --show-current   # must be a feature branch (feat/, fix/, chore/)
git status -s               # should be clean

If on a protected branch (main/release/hotfix/dev): STOP, wrong branch. If dirty: warn user, don't proceed until resolved.

Phase 3: Execute

For each task in the plan, in order:

3.1 Read Context

  • Read the Mirror / Read first references from the plan
  • Understand the pattern before writing code

3.2 Implement

  • Make the change as specified in the task
  • Follow the mirrored pattern exactly

3.3 Validate Immediately

After EVERY file change:

cd codegraph && python -m compileall codegraph/ -q   # syntax check
.venv/bin/python -m pytest tests/ -q                  # tests

If validation fails:

  1. Read the error
  2. Fix the issue
  3. Re-run validation
  4. Only proceed to next task when passing

3.4 Track Progress

Use TaskCreate/TaskUpdate to track each task. Mark in_progress when starting, completed when done.

Task 1: UPDATE codegraph/resolver.py ✅
Task 2: CREATE tests/test_new.py ✅
Task 3: UPDATE codegraph/cli.py ⏳ (in progress)

If you deviate from the plan, note what changed and why.

Phase 4: Final Validation

After all tasks complete:

cd codegraph
python -m compileall codegraph/ -q        # byte-compile
.venv/bin/python -m pytest tests/ -q      # full test suite
.venv/bin/codegraph --help                # CLI sanity

All must pass with zero errors.

Phase 5: Report

Implementation Complete
-----------------------
Plan: {plan-path}
Tasks: {N}/{N} completed
Tests: {N} passed, {N} new
Deviations: {none | list}

Ready for: /review-pr

Read the full file on GitHub · 98 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 · 98 lines · 7 tokens per session scan A 525462ccf912

Subscribe to this mod's changes

implement is a command published in the GitHub repository cognitx-leyton/codegraph (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 7 tokens to every session and 614 once invoked, about $0.0000 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 2026-08-30.