New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Review Harness

by SteelMorgan in SteelMorgan/1c-agent-based-dev-framework

Shared harness library for multi-model review tools (consilium, review-swarm): CLI adapters contract start/ask/fork/status/close/sync, native fork lineage, sandbox-lifecycle, structured-parsing…

Custom licenceAuto-check passed

Install Review Harness

skills CLI
$ npx skills add SteelMorgan/1c-agent-based-dev-framework --skill review-harness -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install SteelMorgan/1c-agent-based-dev-framework review-harness --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/SteelMorgan/1c-agent-based-dev-framework.git skills-src && mkdir -p .claude/skills && cp -r skills-src/framework/skills/tool-usage/review/review-harness .claude/skills/review-harness && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
review-harness
GitHub stars
115
Token cost
~5k tokens
SKILL.md length
1,743 words
Files
51 (incl. scripts, references)
Skills in repo
12
Repo updated
First seen
Licence
Custom licence

At a glance

Shared harness library for multi-model review tools (consilium, review-swarm): CLI adapters contract start/ask/fork/status/close/sync, native fork lineage, sandbox-lifecycle, structured-parsing…

  • Works in 3 steps: Floor-фильтр ПЕРЕД взвешиванием:… → Weighted (детерминированный argmax… → Иначе — blind (равномерная ротация по…
  • SKILL.md covers Правило границы (FR-01, AC-01), Состав библиотеки, Как подключать библиотеку… and Тесты
  • Runs Python scripts from its folder; calls python3

What it does

Review Harness is an agent skill from SteelMorgan/1c-agent-based-dev-framework. Shared harness library for multi-model review tools (consilium, review-swarm): CLI adapters contract start/ask/fork/status/close/sync, native fork lineage, sandbox-lifecycle, structured-parsing, unified adapters registry v3, rotation/domains, track record, heartbeat/progress, quota-aware selection. Library, not a user-facing skill.

Its SKILL.md is about 5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 53 other files, including scripts and reference files (for example `adapters.yaml`, `domains.yaml` and `references/adapter-contract.md`).

The repository describes itself as: Фреймворк агентной разработки на 1С.

Example prompts

  • “/review-harness”

Requirements

  • Python 3

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Floor-фильтр ПЕРЕД взвешиванием: enabled, id != id вызывающего,
  2. Weighted (детерминированный argmax remaining_percent, запрет повтора
  3. Иначе — blind (равномерная ротация по порядку реестра, запрет повтора)

What it can do on your machine

Read from SKILL.md and the folder at commit 8d188b3. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 13 files in scripts/ (Python, from the files we listed), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Review Harness loads about 5k tokens when it runs, and up to ~8.7k if it reads all its reference files. Until then it costs about 87 tokens; SKILL.md has 1,743 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~87
When it runs · the whole SKILL.md, loaded when a task matches
~5k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~8.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 1,743 words (~5,008 tokens).

“Это библиотека, а не инструмент и не playbook вызывающего. Harness — общий слой переиспользуемого транспорта и учёта для инструментов мультимодельного ревью; у него нет собственного CLI для вызывающего агента и нет протокола. Потребители — ровно два инструмента:”

— opening of SKILL.md by SteelMorgan, Custom licence
name
review-harness
capabilities
agent-governance,multi-model-review,cross-provider,harness

Read the full SKILL.md on GitHub

Files

SKILL.md and 50 other files (scripts, references) in framework/skills/tool-usage/review/review-harness of SteelMorgan/1c-agent-based-dev-framework.

  • SKILL.md
  • adapters.yaml
  • domains.yaml
  • references/adapter-contract.md
  • references/track-record-schema.md
  • scripts/adapter_contract.py
  • scripts/adapters/claude_opus_review.py
  • scripts/adapters/codex_app_server.py
  • scripts/adapters/codex_review.py
  • scripts/adapters/kimi_review.py
  • scripts/adapters/kimi_web_fork.py
  • scripts/domains.py
  • scripts/invocation_lock.py
  • scripts/liveness.py
  • scripts/progress.py
  • scripts/quota.py
  • scripts/registry.py
  • scripts/runtime_store.py
  • … and 33 more

Open the folder on GitHubat commit 8d188b3

Similar skills

  • Agent Consilium

    SteelMorgan/1c-agent-based-dev-framework

    MUST use WHEN an architectural or requirements question has material trade-offs that need structured multi-model deliberation (Claude/GPT/Kimi) with adversarial critique and moderator synthesis…

    115 GitHub stars~5.4k tokensUpdated 11 days ago
    Auto-check passed

More from SteelMorgan/1c-agent-based-dev-framework

All 12 skills in this repo

  • Playwright

    SteelMorgan/1c-agent-based-dev-framework

    Browser UI automation: сценарии, формы, скриншоты. An agent skill from SteelMorgan/1c-agent-based-dev-framework.

    115 GitHub stars~589 tokensUpdated 11 days ago
    Auto-check passed

  • Review Swarm

    SteelMorgan/1c-agent-based-dev-framework

    MUST use WHEN a code diff needs second-opinion or multi-model review: light tier = one eligible independent cross-family reviewer selected from enabled participants outside the caller family (also…

    115 GitHub stars~7.9k tokensUpdated 11 days ago
    Auto-check passed

  • Brainstorm

    SteelMorgan/1c-agent-based-dev-framework

    A skill your agent uses for структурированного мозгового штурма при выборе подхода, поиске альтернатив или явном вызове /brainstorm.

    115 GitHub stars~4.1k tokensUpdated 11 days ago
    Auto-check passed

  • Brainstorm

    SteelMorgan/1c-agent-based-dev-framework

    A skill your agent uses for structured brainstorming when choosing an approach, searching for alternatives, or explicitly calling /brainstorm.

    115 GitHub stars~4.3k tokensUpdated 11 days ago
    Auto-check passed

  • Codex Image Gen

    SteelMorgan/1c-agent-based-dev-framework

    Для генерации и редактирования изображений и макетов. An agent skill from SteelMorgan/1c-agent-based-dev-framework.

    115 GitHub stars~1.8k tokensUpdated 11 days ago
    Auto-check passed

  • Codex Image Gen

    SteelMorgan/1c-agent-based-dev-framework

    For generating and editing images and mockups. An agent skill from SteelMorgan/1c-agent-based-dev-framework.

    115 GitHub stars~1.9k tokensUpdated 11 days ago
    Auto-check passed

Questions about Review Harness

What does Review Harness do?

Shared harness library for multi-model review tools (consilium, review-swarm): CLI adapters contract start/ask/fork/status/close/sync, native fork lineage, sandbox-lifecycle, structured-parsing…. Review Harness is an agent skill from SteelMorgan/1c-agent-based-dev-framework. Shared harness library for multi-model review tools (consilium, review-swarm): CLI adapters contract start/ask/fork/status/close/sync, native fork lineage, sandbox-lifecycle, structured-parsing, unified adapters registry v3, rotation/domains, track record, heartbeat/progress, quota-aware selection.

How do I install Review Harness in Claude Code?

Run `npx skills add SteelMorgan/1c-agent-based-dev-framework --skill review-harness -a claude-code`. Or copy the skill folder (framework/skills/tool-usage/review/review-harness in SteelMorgan/1c-agent-based-dev-framework) into .claude/skills/review-harness in your project. Claude Code loads it when a task matches its description.

How do I install Review Harness in Codex?

Run `npx skills add SteelMorgan/1c-agent-based-dev-framework --skill review-harness -a codex`. Or copy the skill folder (framework/skills/tool-usage/review/review-harness in SteelMorgan/1c-agent-based-dev-framework) into .agents/skills/review-harness in your project. Codex loads it when a task matches its description.

Can I use Review Harness in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add SteelMorgan/1c-agent-based-dev-framework --skill review-harness -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/review-harness, .gemini/skills/review-harness, .github/skills/review-harness and .opencode/skills/review-harness in your project.

What does Review Harness need to run?

Going by SKILL.md and its folder, Review Harness needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Review Harness access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Review Harness safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Review Harness use?

Review Harness has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Review Harness use?

About 5k tokens (SKILL.md is roughly 20k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.7k tokens, read only when the agent opens those files.

What are the alternatives to Review Harness?

Skills that share tags, products or a category with Review Harness: Agent Consilium (SteelMorgan/1c-agent-based-dev-framework, 115 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Review Harness?

SteelMorgan (a GitHub user) maintains it in SteelMorgan/1c-agent-based-dev-framework, which has 115 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on September 30, 2026.

Source: SteelMorgan/1c-agent-based-dev-framework on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.