implement-review

A workflow that has one coding agent implement a task and then inspect its own work. It uses a final verification gate that checks whether the requested task was actually completed.

In plain words
What is it for?
Use it for a task, issue, or written change request. It loads context, implements the work, runs simplification and code review, and can run a project-supplied test command before finalizing.
Why use it?
It combines implementation with a required review step, reducing the chance that work is finalized without checking the requirements and tests.

Command

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/sjarmak/coding-agent-workflows/implement-review
Clone the repo
git clone --depth 1 https://github.com/sjarmak/coding-agent-workflows
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,026 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 $0.00020 $0.01026
Opus 5 $0.00010 $0.00513
Sonnet 5 $0.00004 $0.00205
Haiku 4.5 $0.00002 $0.00103

Measured yesterday against content hash ea341a6e83e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

implement-review 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.

targets/claude/commands/implement-review.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Workflow: Implement + Self-Review

The default per-task loop. A single agent implements a change via focus, then runs simplify and code-review as a hard verification gate before finalizing. The gate checks that the work actually fulfills what was asked, not just that the code is stylistically clean.

This is a runtime-neutral spec. It originated as an orchestration formula run by worker agents; the runtime-specific task-tracker and retry calls have been replaced with neutral equivalents so any orchestrator (a Claude Code session, a Codex run, an Amp thread, or a shell loop) can drive it.

Inputs

Input Source Description
task caller The unit of work: a tracker ID, an issue, or a written description.
base_ref caller Base git ref for diff comparison. Default: main.
test_command project Command to verify the work. Empty = skip.

Steps

The steps form a DAG; each lists what it depends on. An orchestrator runs them in dependency order and stops at the gate if it rejects.

1. load-context

Understand the work before touching code. Read the task's description, acceptance criteria, and any linked context. If a prior attempt was rejected, read the rejection reason and target the specific issue it called out.

Exit: you can state what "done" looks like for this task.

2. focus (needs: load-context)

Run the focus skill on the task: plan the implementation, execute the plan step by step, verify against acceptance criteria. Follow the skill's workflow; don't override it. If your context fills up, commit progress and hand off to a fresh session rather than degrading.

Exit: focus has completed its plan → execute → verify cycle.

3. run-tests (needs: focus)

Run test_command. If it's empty, skip. If tests fail: read the output, fix the implementation, commit the fix, re-run. Do not proceed until tests pass.

Exit: tests pass, or no test command is configured.

Read the full file on GitHub · 104 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 · 104 lines · 20 tokens per session scan A ea341a6e83e0

Subscribe to this mod's changes

implement-review is a command published in the GitHub repository sjarmak/coding-agent-workflows (2 stars, last pushed 1mo ago), licensed MIT. It adds 20 tokens to every session and 1,026 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.