O2 Review Loop
openobserve/openobserve
Splits a change into planner, coder and independent reviewer roles: you confirm a spec, a subagent implements it, and a separate reviewer checks each round's local WIP commit.
Reviews a diff before commit: tests can fail, routed rules hold for changed files, unchanged siblings still hold.
Install Agentic Self Review
$ npx skills add carlos-algms/agentic.nvim --skill agentic-self-review -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install carlos-algms/agentic.nvim agentic-self-review --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/carlos-algms/agentic.nvim.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/agentic-self-review .claude/skills/agentic-self-review && rm -rf skills-srcUse ~/.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/
Install the "agentic-self-review" agent skill from https://github.com/carlos-algms/agentic.nvim/tree/main/.agents/skills/agentic-self-review into .claude/skills/agentic-self-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agentic-self-review", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/carlos-algms/agentic.nvim/tree/main/.agents/skills/agentic-self-reviewType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add carlos-algms/agentic.nvim --skill agentic-self-review -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install carlos-algms/agentic.nvim agentic-self-review --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/carlos-algms/agentic.nvim.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/agentic-self-review .agents/skills/agentic-self-review && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "agentic-self-review" agent skill from https://github.com/carlos-algms/agentic.nvim/tree/main/.agents/skills/agentic-self-review into .agents/skills/agentic-self-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agentic-self-review", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add carlos-algms/agentic.nvim --skill agentic-self-review -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install carlos-algms/agentic.nvim agentic-self-review --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/carlos-algms/agentic.nvim.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/agentic-self-review .cursor/skills/agentic-self-review && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "agentic-self-review" agent skill from https://github.com/carlos-algms/agentic.nvim/tree/main/.agents/skills/agentic-self-review into .cursor/skills/agentic-self-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agentic-self-review", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/carlos-algms/agentic.nvim.git --path .agents/skills/agentic-self-review--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add carlos-algms/agentic.nvim --skill agentic-self-review -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install carlos-algms/agentic.nvim agentic-self-review --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/carlos-algms/agentic.nvim.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/agentic-self-review .gemini/skills/agentic-self-review && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "agentic-self-review" agent skill from https://github.com/carlos-algms/agentic.nvim/tree/main/.agents/skills/agentic-self-review into .gemini/skills/agentic-self-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agentic-self-review", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install carlos-algms/agentic.nvim agentic-self-reviewInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add carlos-algms/agentic.nvim --skill agentic-self-review -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/carlos-algms/agentic.nvim.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/agentic-self-review .github/skills/agentic-self-review && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "agentic-self-review" agent skill from https://github.com/carlos-algms/agentic.nvim/tree/main/.agents/skills/agentic-self-review into .github/skills/agentic-self-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agentic-self-review", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add carlos-algms/agentic.nvim --skill agentic-self-review -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install carlos-algms/agentic.nvim agentic-self-review --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/carlos-algms/agentic.nvim.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/agentic-self-review .opencode/skills/agentic-self-review && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "agentic-self-review" agent skill from https://github.com/carlos-algms/agentic.nvim/tree/main/.agents/skills/agentic-self-review into .opencode/skills/agentic-self-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agentic-self-review", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
agentic-self-review- GitHub stars
- 642
- Token cost
- ~760 tokens
- SKILL.md length
- 450 words
- Files
- 1
- Skills in repo
- 8
- Repo updated
- First seen
- Licence
- MIT
At a glance
Reviews a diff before commit: tests can fail, routed rules hold for changed files, unchanged siblings still hold.
- Works in 10 steps: Tests can fail. For each new or changed… → Observable effect. Does an assertion… → Async. No assertion inside a… → …
- Review a diff: yours
- SKILL.md covers Checklist and Output
- Calls make
What it does
Agentic Self Review is an agent skill from carlos-algms/agentic.nvim. Reviews a diff before commit: tests can fail, routed rules hold for changed files, unchanged siblings still hold. Runs no full gate. Use to review a diff: yours, a sub-agent's, or as plan-review loop reviewer.
Its SKILL.md is about 760 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Agent Workflows, covering Code review and Subagents. It works with Lua. The repository describes itself as: Agentic Chat Interface directly in Neovim with ACP providers from Claude-Code, Gemini, Codex, OpenCode, and Cursor-agent. The licence is MIT.
When your agent uses it
- Review a diff: yours
- As plan-review loop reviewer
Example prompts
- “Use the agentic-self-review skill to review a diff before commit: tests can fail, routed rules hold for changed files, unchanged siblings still hold”
- “/agentic-self-review”
Workflow steps
10 steps, taken from the first numbered list in SKILL.md.
- Tests can fail. For each new or changed assertion, name the value that
- Observable effect. Does an assertion read a private field that both the
- Async. No assertion inside a vim.schedule, vim.defer_fn, timer, or
- Cleanup. Stubs reverted before assertions or in after_each; no
- Rule sweep. For each changed file, open every doc its router row names.
- New rules. If the diff adds or edits a rule in any AGENTS.md or skill,
- Siblings. For each fixed or guarded path, read the unchanged sibling
- Transitive context. For code that runs in a libuv callback, follow every
- Docs drift. For each symbol or behavior the diff changes, rg it across
- Rule gaps. Every gap found goes in the Rule gaps list of your final
What it can do on your machine
Read from SKILL.md and the folder at commit 5ee5110. 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
Shell commands in SKILL.md call:
make
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
Agentic Self Review loads about 760 tokens when it runs. Until then it costs about 57 tokens; SKILL.md has 450 words of instructions outside code blocks.
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); files beside SKILL.md are not scanned.
SKILL.md
The full file from carlos-algms/agentic.nvim at commit 5ee5110, republished under its MIT licence (© carlos-algms). 450 words, ~760 tokens.
Download SKILL.mdSave it as
.claude/skills/agentic-self-review/SKILL.md (or your agent's skills folder).- name
- agentic-self-review
- description
- Reviews a diff before commit: tests can fail, routed rules hold for changed files, unchanged siblings still hold. Runs no full gate. Use to review a diff: yours, a sub-agent's, or as plan-review loop reviewer.
Self-review
One review per diff. If this diff already passed a review and no file changed since, do not review it again.
Run read-only commands only, plus make test-file FILE=<path> for the revert
check in step 1. This review trusts the gates that already passed: never run
make validate, make test, lint, or types.
Checklist
Create a task list with these items. Mark each completed only when it is done
for every changed file.
- Tests can fail. For each new or changed assertion, name the value that
would make it fail. None reachable -> the assertion is decoration. For a
bug-fix test, undo the fix, run
make test-file FILE=<path>, confirm red, restore the fix - Observable effect. Does an assertion read a private field that both the correct and the broken branch write? Then it cannot fail. Assert the public effect instead
- Async. No assertion inside a
vim.schedule,vim.defer_fn, timer, or coroutine callback. Store the value, assert in theit()body - Cleanup. Stubs reverted before assertions or in
after_each; no discardedpcallresult; teardown compares handle sets, not counts - Rule sweep. For each changed file, open every doc its router row names. Check every rule in those docs against the diff, not only the rules you remember. Include test mocks: they follow the same rules as production code
- New rules. If the diff adds or edits a rule in any
AGENTS.mdor skill, check that rule against every function in the same diff. A new runtime rule must cite a test - Siblings. For each fixed or guarded path, read the unchanged sibling
paths in the same function and its callers (
rgthe symbol). Does the change's premise make any unchanged line wrong? Apcallin a callee hides a violation: no error, no failing test. Do not treat a caught error as handled until you know what it hid - Transitive context. For code that runs in a libuv callback, follow every call it makes. The fast-event ban applies to the whole call chain
- Docs drift. For each symbol or behavior the diff changes,
rgit acrossdocs/,doc/,README.md,CONTRIBUTING.md, everyAGENTS.md, and.agents/skills/. Re-read each hit against the code. One contract stated in several places drifts in one copy - Rule gaps. Every gap found goes in the
Rule gapslist of your final report: file, rule, what happened. The agent that receives the report appends it torules-report.md. A gap in an area you own is fixed in the same change, per skillagentic-learn
Show full SKILL.md (27 more words)Show less
Output
Report findings as file:symbol - problem - fix. Fix them, or hand them back
to the agent that owns the commit. Report "no findings" when there are none.
© carlos-algms, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .agents/skills/agentic-self-review of carlos-algms/agentic.nvim.
Open the folder on GitHubat commit 5ee5110
Compare with similar skills
Agentic Self Review next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Agentic Self Review this skillcarlos-algms/agentic.nvim | 642 | — | ~760 | Automated safety check: Pass | MIT | |
| O2 Review Loopopenobserve/openobserve | 22k | — | ~3.7k | Automated safety check: Pass | AGPL-3.0 | |
| Elvesaigorahub/elves | 221 | — | ~16k | Automated safety check: Notes | MIT | |
| Subagent-Driven DevelopmentHoangNguyen0403/agent-skills-standard | 572 | — | ~1.3k | Automated safety check: Pass | MIT | |
| Reviewjuliepy/AI-Engineer-from-scrach | 441 | — | ~417 | Automated safety check: Pass | None | |
| Simplifytellahq/opensession | 394 | — | ~834 | Automated safety check: Pass | MIT |
Similar skills
Elves
aigorahub/elves
Autonomous multi-batch development agent for long unattended runs, reviewed-PR landing, Cobbler-first orchestration, and optional Fugu, Manus, Grok, Devin, or Oh My Pi (omp) provider shortcuts.
Subagent-Driven Development
HoangNguyen0403/agent-skills-standard
Runs a multi-task implementation plan by sending each task to a fresh implementer subagent, reviewing it independently, then reviewing the whole branch.
Review
juliepy/AI-Engineer-from-scrach
Delegate the latest implementation diff to the code-reviewer sub-agent for a PASS/CONCERNS verdict against CLAUDE.md rules, then write the verdict to reports/<feature-review.md.
Simplify
tellahq/opensession
Clean up the changed code without changing behavior — review the diff for reuse, simplification, efficiency, and altitude cleanups via 4 parallel agents, then apply the fixes
Agent Architect
IgorWarzocha/Opencode-Workflows
Create and refine OpenCode agents via guided Q&A. An agent skill from IgorWarzocha/Opencode-Workflows.
More from carlos-algms/agentic.nvim
All 11 skills in this repoAgentic GitHub Discussion
carlos-algms/agentic.nvim
Creates, lists, and manages GitHub discussions in this repo through the GraphQL API.
Agentic Learn
carlos-algms/agentic.nvim
Turns rule gaps into routed, verified rules and empties rules-report.md.
Agentic Testing
carlos-algms/agentic.nvim
MANDATORY before creating, editing, or reviewing tests in agentic.nvim, and before behavior changes that require TDD.
Agentic Lua Class
carlos-algms/agentic.nvim
Enforced Lua style: class pattern, visibility prefixes (private, protected), optional-type syntax, LuaCATS annotations.
Agentic Vimdoc
carlos-algms/agentic.nvim
A skill your agent uses when writing or updating agentic.nvim vimdoc (doc/agentic.txt), or after changing init.lua, configdefault.lua, theme.lua, or README install/keymaps - those edits require a…
Agentic Acp Docs And Schema
carlos-algms/agentic.nvim
Official ACP schema, events, and rules for this plugin's provider work.
Related
Works with
Categories
Questions about Agentic Self Review
What does Agentic Self Review do?
Reviews a diff before commit: tests can fail, routed rules hold for changed files, unchanged siblings still hold. nvim. Reviews a diff before commit: tests can fail, routed rules hold for changed files, unchanged siblings still hold.
When should I use Agentic Self Review?
Agentic Self Review fits situations like: review a diff: yours; as plan-review loop reviewer.
How do I install Agentic Self Review in Claude Code?
Run `npx skills add carlos-algms/agentic.nvim --skill agentic-self-review -a claude-code`. Or copy the skill folder (.agents/skills/agentic-self-review in carlos-algms/agentic.nvim) into .claude/skills/agentic-self-review in your project. Claude Code loads it when a task matches its description.
How do I install Agentic Self Review in Codex?
Run `npx skills add carlos-algms/agentic.nvim --skill agentic-self-review -a codex`. Or copy the skill folder (.agents/skills/agentic-self-review in carlos-algms/agentic.nvim) into .agents/skills/agentic-self-review in your project. Codex loads it when a task matches its description.
Can I use Agentic Self Review 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 carlos-algms/agentic.nvim --skill agentic-self-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agentic-self-review, .gemini/skills/agentic-self-review, .github/skills/agentic-self-review and .opencode/skills/agentic-self-review in your project.
What does Agentic Self Review need to run?
Going by SKILL.md and its folder, Agentic Self Review needs the command-line tools its instructions call (make).
Does Agentic Self Review 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 Agentic Self Review 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. Review the folder before installing.
What licence does Agentic Self Review use?
Agentic Self Review is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Agentic Self Review use?
About 760 tokens (SKILL.md is roughly 3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Agentic Self Review?
Skills that share tags, products or a category with Agentic Self Review: O2 Review Loop (openobserve/openobserve, 22k stars), Elves (aigorahub/elves, 221 stars), Subagent-Driven Development (HoangNguyen0403/agent-skills-standard, 572 stars) and Review (juliepy/AI-Engineer-from-scrach, 441 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Agentic Self Review?
carlos-algms (a GitHub user) maintains it in carlos-algms/agentic.nvim, which has 642 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on October 10, 2026.
Source: carlos-algms/agentic.nvim on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.