review-implementation

A review workflow that checks an implementation against its stated requirements, type declarations, code-quality rules, and tests.

In plain words
What is it for?
Use it to review a completed Python implementation and its tests, including whether the source matches its .pyi interface files.
Why use it?
It helps catch missing behavior, unnecessary changes, code smells, mismatched type information, and broken tests before accepting the work.

Skill for Claude CodeCodex

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/nullhack/temple8/review-implementation
Any agent
npx skills add nullhack/temple8 --skill review-implementation
Clone the repo
git clone --depth 1 https://github.com/nullhack/temple8

Made for: Claude Code, Codex.

Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 316 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 $0.00021 $0.00316
Opus 5 $0.00010 $0.00158
Sonnet 5 $0.00004 $0.00063
Haiku 4.5 $0.00002 $0.00032

Measured yesterday against content hash b079fc2662ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review-implementation 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.

.opencode/skills/review-implementation/SKILL.md · 16 lines

What it actually says

Review Implementation

  1. Load [[software-craft/code-review]], [[software-craft/solid]], [[software-craft/smell-catalogue]], [[software-craft/design-patterns]] — review method, quality criteria, smell taxonomy, and the pattern catalog.
  2. Review the implemented source against its contract per [[software-craft/code-review]].
  3. Check impl-matches-contract: the .py satisfies its .pyi and the requirement, without excess.
  4. Check source-quality-clean: IF SOLID, DRY, KISS, YAGNI, Object Calisthenics are violated OR a smell is present THEN reject per [[software-craft/solid]], [[software-craft/smell-catalogue]].
  5. Check stubtest-clean: the source .py and its sibling .pyi agree, AND the target's test .py and its sibling .pyi agree — no drift on either pair.
  6. Check tests-green: the target's tests pass and no previously-green test regressed.
  7. Read the target's .pyi first; open the .py only for the spots under review.
  8. IF review reveals the contract itself is the problem — not the implementation — THEN append the finding to .cache/<session_id>/journal.md (contract, the gap, the evidence) and fire reveals-gap. This routes back to plan, not changes-needed.
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 · 16 lines · 21 tokens per session scan A b079fc2662ad

Subscribe to this mod's changes

review-implementation is a skill published in the GitHub repository nullhack/temple8 (11 stars, last pushed 27d ago), licensed MIT. It adds 21 tokens to every session and 316 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 2026-08-30.