implementation-plan-review

implementation-plan-review is a skill for Claude Code, Codex from akolotov/harness. It costs 41 tokens per session (2,443 once invoked), scanned A, original, MIT.

A review skill for comparing an implementation plan with its GitHub issue and the existing codebase. It checks correctness, completeness, risks, and whether the plan is ready to test.

In plain words
What is it for?
Reviewing a local plan against requirements and source code, including checking test coverage and implementation risks.
Why use it?
It helps find missing work or unsafe assumptions before coding begins, when changes are still easier to make.

Skill for Claude CodeCodex

Written for Claude Code and Codex: disable-model-invocation in frontmatter, but also agents/openai.yaml present. Also seen: mentions CLAUDE.md; mentions subagents; mentions AGENTS.md.

Part of the ak-dev plugin — 5 skills shipped together

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 skills/akolotov/harness/implementation-plan-review
Any agent
npx skills add akolotov/harness --skill implementation-plan-review
Clone the repo
git clone --depth 1 https://github.com/akolotov/harness

Made for: Claude Code, Codex.

Or install ak-dev, the plugin that ships this one along with the rest of its 5 skills.

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 implementation-plan-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/akolotov/harness/implementation-plan-review.svg)](https://agentmods.dev/skills/akolotov/harness/implementation-plan-review)
Your own site
<a href="https://agentmods.dev/skills/akolotov/harness/implementation-plan-review"><img src="https://agentmods.dev/badge/skills/akolotov/harness/implementation-plan-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,443 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 5.1 $0.00041 $0.02443
Opus 5 $0.00020 $0.01222
Sonnet 5 $0.00008 $0.00489
Haiku 4.5 $0.00004 $0.00244

Measured 6d ago against content hash a926be603838, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

implementation-plan-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 6d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/_adjudication_report.py, scripts/fetch_github_issue.sh, scripts/finalize_adjudication.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

dev/skills/implementation-plan-review/SKILL.md · 228 lines

How it starts

The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implementation Plan Review (Expert)

Review an implementation plan for coverage, correctness, and fit with the current codebase. Do not implement.

Inputs

  • Implementation plan: a local file path.
  • Issue/requirements: either (a) a local file path, or (b) a GitHub issue number (run from the target repo so gh resolves it).

Every relative path in this skill — scripts, references, and assets — resolves from the directory that holds this SKILL.md, not from the current working directory. Resolve each one against that directory before running or reading it.

If the user provides a GitHub issue number, prefer fetching it into a local file using the bundled script:

bash scripts/fetch_github_issue.sh <issue-number> --out /tmp/issue.md

Run this command from the skill directory when that directory is inside the target repository. If it is not, keep the command agent-agnostic by resolving the script path relative to this skill directory while running gh from the target repo so the issue number resolves against the correct repository.

Fetching is a network operation. When command execution is sandboxed, request network escalation (require_escalated) for this exact fetch command rather than granting a reusable broad bash permission. On failure, follow the script's self-contained ACTION line. It distinguishes unavailable network (exit 6), credentials unavailable to the process (exit 3), other GitHub fetch failures (exit 4), and local output failures (exit 5).

Workflow

  1. Prepare a clean review run:
    • Before reading or listing any scratchpad files, run from this skill directory:
bash scripts/new_scratchpads_dir.sh <plan-file>
  • Use exactly the absolute path the script printed on stdout as this review's run directory; never glob or guess a path under scratchpads/ yourself.
  • Each run creates a fresh timestamped directory (scratchpads/<YYMMDD-HHMM>/); nothing is deleted. Directories from earlier reviews belong to a different run — never read or reuse them for this review. (If the printed path is ever lost from context, the lexicographically-last timestamp subdirectory is the most recent, since the format sorts chronologically — but prefer the printed path.)
  • If the script fails (non-zero exit; error: <message> on stderr), stop and report the failure.

Read the full file on GitHub · 228 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 · 228 lines · 41 tokens per session scan A a926be603838

Subscribe to this mod's changes

implementation-plan-review is a skill published in the GitHub repository akolotov/harness (2 stars, last pushed 5d ago), licensed MIT. It adds 41 tokens to every session and 2,443 once invoked, about $0.0002 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.