Claude Code Agent Development
anthropics/claude-plugins-official
Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.
A skill your agent uses when Codex or OpenCode repeats avoidable mistakes, keeps guessing after failures, fails to trigger an expected skill/workflow/subagent, or the user corrects agent behavior…
Install Self Correction Loop
$ npx skills add skuramatata/my-pi-agent --skill self-correction-loop -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install skuramatata/my-pi-agent self-correction-loop --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/skuramatata/my-pi-agent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.opencode/skills/self-correction-loop .claude/skills/self-correction-loop && 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 "self-correction-loop" agent skill from https://github.com/skuramatata/my-pi-agent/tree/main/.opencode/skills/self-correction-loop into .claude/skills/self-correction-loop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "self-correction-loop", 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/skuramatata/my-pi-agent/tree/main/.opencode/skills/self-correction-loopType 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 skuramatata/my-pi-agent --skill self-correction-loop -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install skuramatata/my-pi-agent self-correction-loop --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/skuramatata/my-pi-agent.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.opencode/skills/self-correction-loop .agents/skills/self-correction-loop && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "self-correction-loop" agent skill from https://github.com/skuramatata/my-pi-agent/tree/main/.opencode/skills/self-correction-loop into .agents/skills/self-correction-loop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "self-correction-loop", 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 skuramatata/my-pi-agent --skill self-correction-loop -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install skuramatata/my-pi-agent self-correction-loop --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/skuramatata/my-pi-agent.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.opencode/skills/self-correction-loop .cursor/skills/self-correction-loop && 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 "self-correction-loop" agent skill from https://github.com/skuramatata/my-pi-agent/tree/main/.opencode/skills/self-correction-loop into .cursor/skills/self-correction-loop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "self-correction-loop", 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/skuramatata/my-pi-agent.git --path .opencode/skills/self-correction-loop--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 skuramatata/my-pi-agent --skill self-correction-loop -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install skuramatata/my-pi-agent self-correction-loop --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/skuramatata/my-pi-agent.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.opencode/skills/self-correction-loop .gemini/skills/self-correction-loop && 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 "self-correction-loop" agent skill from https://github.com/skuramatata/my-pi-agent/tree/main/.opencode/skills/self-correction-loop into .gemini/skills/self-correction-loop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "self-correction-loop", 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 skuramatata/my-pi-agent self-correction-loopInstalls 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 skuramatata/my-pi-agent --skill self-correction-loop -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/skuramatata/my-pi-agent.git skills-src && mkdir -p .github/skills && cp -r skills-src/.opencode/skills/self-correction-loop .github/skills/self-correction-loop && 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 "self-correction-loop" agent skill from https://github.com/skuramatata/my-pi-agent/tree/main/.opencode/skills/self-correction-loop into .github/skills/self-correction-loop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "self-correction-loop", 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 skuramatata/my-pi-agent --skill self-correction-loop -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install skuramatata/my-pi-agent self-correction-loop --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/skuramatata/my-pi-agent.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.opencode/skills/self-correction-loop .opencode/skills/self-correction-loop && 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 "self-correction-loop" agent skill from https://github.com/skuramatata/my-pi-agent/tree/main/.opencode/skills/self-correction-loop into .opencode/skills/self-correction-loop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "self-correction-loop", 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
self-correction-loop- GitHub stars
- 114
- Token cost
- ~1.5k tokens
- SKILL.md length
- 834 words
- Files
- 1
- Skills in repo
- 24
- Repo updated
- First seen
- Licence
- None found
At a glance
A skill your agent uses when Codex or OpenCode repeats avoidable mistakes, keeps guessing after failures, fails to trigger an expected skill/workflow/subagent, or the user corrects agent behavior…
- Works in 5 steps: Acknowledge the failure mode briefly in… → Freeze the current assumption: state… → Inspect the authoritative layer before… → …
- OpenCode repeats avoidable mistakes
- SKILL.md covers Core Principle, Trigger Response, Memory Scope and Red Flags, plus 4 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Self Correction Loop is an agent skill from skuramatata/my-pi-agent. Use when Codex or OpenCode repeats avoidable mistakes, keeps guessing after failures, fails to trigger an expected skill/workflow/subagent, or the user corrects agent behavior, assumptions, scope, or process with phrases like 不对, 不是, 偷懒, 自我进化, 自我修正, 每次都这样, or similar frustration in this repository.
Its SKILL.md is about 1.5k 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 Subagents.
When your agent uses it
- OpenCode repeats avoidable mistakes
- Keeps guessing after failures
- Fails to trigger an expected skill/workflow/subagent
- The user corrects agent behavior
Example prompts
- “/self-correction-loop”
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Acknowledge the failure mode briefly in Chinese.
- Freeze the current assumption: state exactly what was assumed and what contradicted it.
- Inspect the authoritative layer before another attempt
- Define a next-attempt contract
- Execute the smallest next step and report the result.
What it can do on your machine
Read from SKILL.md and the folder at commit ed83ff1. 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
No scripts in the folder and no shell commands in SKILL.md.
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
Self Correction Loop loads about 1.5k tokens when it runs. Until then it costs about 80 tokens; SKILL.md has 834 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
Without a licence we can't republish the file, so here is its outline and opening line. It has 834 words (~1,531 tokens).
“When work starts drifting into guesswork, stop trying more actions. Convert the failure into a concrete constraint for the next attempt, then continue only with evidence from source code, runtime state, or tests.”
- name
- self-correction-loop
Files
Just SKILL.md in .opencode/skills/self-correction-loop of skuramatata/my-pi-agent.
Open the folder on GitHubat commit ed83ff1
Compare with similar skills
Self Correction Loop 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 |
|---|---|---|---|---|---|---|
| Self Correction Loop this skillskuramatata/my-pi-agent | 114 | — | ~1.5k | Automated safety check: Pass | None | |
| Claude Code Agent Developmentanthropics/claude-plugins-official | 38k | 7 repos | ~2.8k | Automated safety check: Pass | Apache-2.0 | |
| Subagent Driven DevelopmentAsvarox/allkaraoke | 261 | 37 repos | ~1.2k | Automated safety check: Pass | None | |
| Dispatching Parallel Agentsultralisp/ultralisp | 258 | 40 repos | ~1.5k | Automated safety check: Pass | None | |
| Paseo Advisor Second Opiniongetpaseo/paseo | 20k | 1 repos | ~756 | Automated safety check: Pass | Custom licence | |
| Task Observerrebelytics/one-skill-to-rule-them-all | 3.2k | 1 repos | ~12k | Automated safety check: Pass | CC-BY-4.0 |
Similar skills
- Official
Subagent Driven Development
Asvarox/allkaraoke
A skill your agent uses when executing implementation plans with independent tasks in the current session
Dispatching Parallel Agents
ultralisp/ultralisp
A skill your agent uses when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
Paseo Advisor Second Opinion
getpaseo/paseo
Launches one separate agent through Paseo to give a second opinion on the current task, with a self-contained briefing and no permission to edit files.
Task Observer
rebelytics/one-skill-to-rule-them-all
Monitors task execution for skill improvement opportunities.
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.
More from skuramatata/my-pi-agent
All 24 skills in this repoDocumentation And Adrs
skuramatata/my-pi-agent
A skill your agent uses when my-pi-agent changes architecture, runtime/workflow/executor behavior, prompt-engine contracts, memory/state, channel behavior, MCP/OpenCode config, README content, or…
Documentation And Adrs
skuramatata/my-pi-agent
A skill your agent uses when my-pi-agent changes architecture, orchestration, execution, prompt-engine, memory, Feishu/channel behavior, skill scope, verifier semantics, public commands, or…
Openspec Apply Change
skuramatata/my-pi-agent
A skill your agent uses when the user wants to implement, continue, or work through tasks from an existing OpenSpec change.
Openspec Propose
skuramatata/my-pi-agent
A skill your agent uses when the user wants to propose a new OpenSpec change and generate proposal, design, specs, and tasks before implementation.
Code Review
skuramatata/my-pi-agent
A skill your agent uses when reviewing a my-pi-agent change before merge or handoff: 代码审查、review、PR review、改动盘点、merge readiness、风险找漏、提交前质量检查。
Code Review And Quality
skuramatata/my-pi-agent
A skill your agent uses when reviewing my-pi-agent changes, PRs, worker output, verifier repair results, prompt/skill edits, Feishu channel changes, or shared runtime refactors.
Related
Categories
Questions about Self Correction Loop
What does Self Correction Loop do?
A skill your agent uses when Codex or OpenCode repeats avoidable mistakes, keeps guessing after failures, fails to trigger an expected skill/workflow/subagent, or the user corrects agent behavior…. Self Correction Loop is an agent skill from skuramatata/my-pi-agent. Use when Codex or OpenCode repeats avoidable mistakes, keeps guessing after failures, fails to trigger an expected skill/workflow/subagent, or the user corrects agent behavior, assumptions, scope, or process with phrases like 不对, 不是, 偷懒, 自我进化, 自我修正, 每次都这样, or similar frustration in this repository.
When should I use Self Correction Loop?
Self Correction Loop fits situations like: openCode repeats avoidable mistakes; keeps guessing after failures; fails to trigger an expected skill/workflow/subagent; the user corrects agent behavior.
How do I install Self Correction Loop in Claude Code?
Run `npx skills add skuramatata/my-pi-agent --skill self-correction-loop -a claude-code`. Or copy the skill folder (.opencode/skills/self-correction-loop in skuramatata/my-pi-agent) into .claude/skills/self-correction-loop in your project. Claude Code loads it when a task matches its description.
How do I install Self Correction Loop in Codex?
Run `npx skills add skuramatata/my-pi-agent --skill self-correction-loop -a codex`. Or copy the skill folder (.opencode/skills/self-correction-loop in skuramatata/my-pi-agent) into .agents/skills/self-correction-loop in your project. Codex loads it when a task matches its description.
Can I use Self Correction Loop 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 skuramatata/my-pi-agent --skill self-correction-loop -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/self-correction-loop, .gemini/skills/self-correction-loop, .github/skills/self-correction-loop and .opencode/skills/self-correction-loop in your project.
What does Self Correction Loop need to run?
SKILL.md names no scripts, command-line tools or credentials: Self Correction Loop is instructions for the agent only.
Does Self Correction Loop 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 Self Correction Loop 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 Self Correction Loop use?
No licence was found for Self Correction Loop or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does Self Correction Loop use?
About 1.5k tokens (SKILL.md is roughly 6.1k 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 Self Correction Loop?
Skills that share tags, products or a category with Self Correction Loop: Claude Code Agent Development (anthropics/claude-plugins-official, 38k stars), Subagent Driven Development (Asvarox/allkaraoke, 261 stars), Dispatching Parallel Agents (ultralisp/ultralisp, 258 stars) and Paseo Advisor Second Opinion (getpaseo/paseo, 20k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Self Correction Loop?
skuramatata (a GitHub user) maintains it in skuramatata/my-pi-agent, which has 114 GitHub stars. The repository holds 24 skills in this directory. The repository was last updated on July 10, 2026.
Source: skuramatata/my-pi-agent on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.