Agent Introspection Debugging
affaan-m/ECC
Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports.
Loop-breaking self-diagnosis. An agent skill from hashgraph-online/awesome-codex-plugins.
Apache-2.0Auto-check passed
Install Agent Introspection
$ npx skills add hashgraph-online/awesome-codex-plugins --skill agent-introspection -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins agent-introspection --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/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/epicsagas/epic-harness/skills/agent-introspection .claude/skills/agent-introspection && 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 "agent-introspection" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/epicsagas/epic-harness/skills/agent-introspection into .claude/skills/agent-introspection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-introspection", 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/hashgraph-online/awesome-codex-plugins/tree/main/plugins/epicsagas/epic-harness/skills/agent-introspectionType 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 hashgraph-online/awesome-codex-plugins --skill agent-introspection -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins agent-introspection --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/epicsagas/epic-harness/skills/agent-introspection .agents/skills/agent-introspection && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "agent-introspection" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/epicsagas/epic-harness/skills/agent-introspection into .agents/skills/agent-introspection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-introspection", 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 hashgraph-online/awesome-codex-plugins --skill agent-introspection -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins agent-introspection --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/epicsagas/epic-harness/skills/agent-introspection .cursor/skills/agent-introspection && 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 "agent-introspection" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/epicsagas/epic-harness/skills/agent-introspection into .cursor/skills/agent-introspection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-introspection", 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/hashgraph-online/awesome-codex-plugins.git --path plugins/epicsagas/epic-harness/skills/agent-introspection--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 hashgraph-online/awesome-codex-plugins --skill agent-introspection -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins agent-introspection --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/epicsagas/epic-harness/skills/agent-introspection .gemini/skills/agent-introspection && 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 "agent-introspection" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/epicsagas/epic-harness/skills/agent-introspection into .gemini/skills/agent-introspection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-introspection", 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 hashgraph-online/awesome-codex-plugins agent-introspectionInstalls 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 hashgraph-online/awesome-codex-plugins --skill agent-introspection -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/epicsagas/epic-harness/skills/agent-introspection .github/skills/agent-introspection && 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 "agent-introspection" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/epicsagas/epic-harness/skills/agent-introspection into .github/skills/agent-introspection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-introspection", 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 hashgraph-online/awesome-codex-plugins --skill agent-introspection -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins agent-introspection --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/epicsagas/epic-harness/skills/agent-introspection .opencode/skills/agent-introspection && 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 "agent-introspection" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/epicsagas/epic-harness/skills/agent-introspection into .opencode/skills/agent-introspection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-introspection", 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
agent-introspection- GitHub stars
- 1.3k
- Token cost
- ~960 tokens
- SKILL.md length
- 428 words
- Files
- 1
- Skills in repo
- 714
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Loop-breaking self-diagnosis. An agent skill from hashgraph-online/awesome-codex-plugins.
- Works in 4 steps: Failure Capture → Root Cause Diagnosis → Controlled Recovery → …
- 3+ consecutive failures occur
- SKILL.md covers Iron Law, When to Trigger, Process and Anti-Rationalization, plus 2 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Agent Introspection is an agent skill from hashgraph-online/awesome-codex-plugins. Loop-breaking self-diagnosis. Use when 3+ consecutive failures occur, circular retries persist, or context overwhelms the session.
Its SKILL.md is about 960 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
The repository describes itself as: A curated list of awesome OpenAI Codex / ChatGPT plugins, skills, and resources. The 1 Codex Marketplace. See live plugins at: https://hol.org/plugins/best-codex-plugins. The licence is Apache-2.0.
When your agent uses it
- 3+ consecutive failures occur
- Circular retries persist
- Context overwhelms the session
Example prompts
- “/agent-introspection”
Workflow steps
4 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 9e7b281. 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 (its code samples are markdown and bash).
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
Agent Introspection loads about 960 tokens when it runs. Until then it costs about 38 tokens; SKILL.md has 428 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 hashgraph-online/awesome-codex-plugins at commit 9e7b281, republished under its Apache-2.0 licence (© hashgraph-online). 428 words, ~960 tokens.
Download SKILL.mdSave it as
.claude/skills/agent-introspection/SKILL.md (or your agent's skills folder).- name
- agent-introspection
- description
- Loop-breaking self-diagnosis. Use when 3+ consecutive failures occur, circular retries persist, or context overwhelms the session.
Agent Introspection — Systematic Self-Diagnosis
Iron Law
NO UNSUPPORTED SELF-HEALING CLAIMS. Only assert recovery actions you can actually perform with available tools.
When to Trigger
- 3+ consecutive failures on the same task
- Repeating the same approach with different parameters (loop detection)
- Context window exceeds 70% without resolution
- Error messages repeat with no progress
- User explicitly says "you're stuck" or "try a different approach"
Process
1. Failure Capture
Stop immediately and record:
- Error type: syntax_error / type_error / test_fail / lint_fail / build_fail / runtime_error / permission_denied / not_found
- Last 3 tool calls: what was attempted and what failed
- Context pressure: approximate context usage percentage
- What changed: what was the last successful state
2. Root Cause Diagnosis
Match against known patterns:
| Pattern | Symptoms | Root Cause |
|---|---|---|
| Loop trap | Same error 3+ times | Wrong approach, not wrong parameters |
| Context overflow | Increasingly confused responses | Too much information, need compaction |
| Environment drift | "Works locally" failures | Missing env var, different tool version |
| Cascade failure | Fix A breaks B | Underlying assumption is wrong |
| Tool mismatch | Wrong tool for the job | Need a different approach entirely |
3. Controlled Recovery
Execute ONLY the smallest safe action:
- Loop trap → Abandon current approach entirely. Try a fundamentally different strategy.
- Context overflow → Run
/compactor summarize current state, then continue. - Environment drift → Verify environment with explicit checks (
which,--version). - Cascade failure → Revert to last known good state. Re-analyze assumptions.
- Tool mismatch → Switch tools. If
Editfails 3 times, tryWrite. IfBashfails, tryReadfirst.
4. Introspection Report
Generate a structured report:
## Introspection Report
- **Failure type**: [type]
- **Root cause**: [diagnosis]
- **Recovery action**: [what was done]
- **Confidence**: [high/medium/low]
- **Next step**: [what to do if this happens again]Save to memory:
epic mem add \
--title "Self-diagnosis: {error_type} in {file}" \
--type error \
--body "Pattern: ...\nRoot cause: ...\nRecovery: ...\n"Show full SKILL.md (182 more words)Show less
Anti-Rationalization
| Excuse | Rebuttal | What to do instead |
|---|---|---|
| "One more try might work" | 3 failures means the approach is wrong, not unlucky. | Stop and run the full 4-step introspection process. |
| "I just need to tweak the parameters" | Tweaking a failing approach is not debugging. Step back and reassess. | Abandon the current approach and try a fundamentally different strategy. |
| "I can fix this myself" | Asking for help is not weakness. Escalation saves everyone time. | Escalate to the user with a clear summary of what was tried and what failed. |
| "The error is clear, I know the fix" | You said that 3 times already. Prove it with a different approach. | Run the introspection report and verify the fix with a test before claiming success. |
Evidence Required
- Failure type classified correctly
- Root cause matched to known pattern
- Recovery action is the smallest safe action
- Introspection report generated
- Failure pattern recorded in memory
Red Flags
- Trying the same command more than 3 times with minor variations
- Claiming "fixed!" without running the actual test
- Not recording the failure pattern in memory
- Continuing after 70% context usage without compacting
© hashgraph-online, Apache-2.0. 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 plugins/epicsagas/epic-harness/skills/agent-introspection of hashgraph-online/awesome-codex-plugins.
Open the folder on GitHubat commit 9e7b281
Compare with similar skills
Agent Introspection 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 |
|---|---|---|---|---|---|---|
| Agent Introspection this skillhashgraph-online/awesome-codex-plugins | 1.3k | — | ~960 | Automated safety check: Pass | Apache-2.0 | |
| Agent Introspection Debuggingaffaan-m/ECC | 276k | 2 repos | ~1.4k | Automated safety check: Pass | MIT | |
| Dart Log Failure Parserflutter/flutter | 179k | — | ~489 | Automated safety check: Pass | BSD-3-Clause | |
| V5 Breaking Changesremotion-dev/remotion | 63k | — | ~879 | Automated safety check: Pass | Custom licence | |
| Investigating CI FailuresPostHog/posthog | 40k | — | ~2.9k | Automated safety check: Pass | Custom licence | |
| Agent Introspection Debuggingaffaan-m/ECC | 276k | — | ~763 | Automated safety check: Pass | MIT |
Similar skills
Dart Log Failure Parser
flutter/flutter
Parse failures from Dart and Flutter test logs. An agent skill from flutter/flutter.
- Official
V5 Breaking Changes
remotion-dev/remotion
Implement or review a Remotion 5 breaking change while the v4 and v5 release lines still share code.
- Official
Investigating CI Failures
PostHog/posthog
Investigates a specific CI failure to a verdict: whose fault, which commit, who wrote it, and whether it's fixed.
Agent Introspection Debugging
affaan-m/ECC
キャプチャ、診断、封じ込め回復、内省レポートを使用した AI エージェント障害のための構造化された自己デバッグワークフロー。
Agent Introspection Debugging
affaan-m/ECC
针对AI代理故障的结构化自调试工作流程，包括捕获、诊断、受限恢复和内省报告。
More from hashgraph-online/awesome-codex-plugins
All 714 skills in this repoAnime Reaction Gif
hashgraph-online/awesome-codex-plugins
Create original anime-style reaction stickers as looping GIFs and MP4 previews, using generated character pose sheets and timed key poses.
Calibredb
hashgraph-online/awesome-codex-plugins
Manage and query Calibre libraries with the calibredb CLI (local paths or Calibre Content server URLs).
Rust API Test Harness
hashgraph-online/awesome-codex-plugins
A skill your agent uses when adding, changing, testing, or debugging Rust HTTP APIs and services, especially when Codex needs black-box integration tests, random-port app startup, real database test…
Art
hashgraph-online/awesome-codex-plugins
Make a studio's game look like something at build time — a cover from a real frame of the game (free), painted covers, backdrops, textures and character plates from image models through the…
Calle
hashgraph-online/awesome-codex-plugins
Use CALL-E from Codex through the calle CLI. An agent skill from hashgraph-online/awesome-codex-plugins.
Game Balance Economy
hashgraph-online/awesome-codex-plugins
Balance game difficulty, resources, rewards, probability, progression, economies, and dominant strategies.
Questions about Agent Introspection
What does Agent Introspection do?
Loop-breaking self-diagnosis. An agent skill from hashgraph-online/awesome-codex-plugins. Agent Introspection is an agent skill from hashgraph-online/awesome-codex-plugins. Loop-breaking self-diagnosis.
When should I use Agent Introspection?
Agent Introspection fits situations like: 3+ consecutive failures occur; circular retries persist; context overwhelms the session.
How do I install Agent Introspection in Claude Code?
Run `npx skills add hashgraph-online/awesome-codex-plugins --skill agent-introspection -a claude-code`. Or copy the skill folder (plugins/epicsagas/epic-harness/skills/agent-introspection in hashgraph-online/awesome-codex-plugins) into .claude/skills/agent-introspection in your project. Claude Code loads it when a task matches its description.
How do I install Agent Introspection in Codex?
Run `npx skills add hashgraph-online/awesome-codex-plugins --skill agent-introspection -a codex`. Or copy the skill folder (plugins/epicsagas/epic-harness/skills/agent-introspection in hashgraph-online/awesome-codex-plugins) into .agents/skills/agent-introspection in your project. Codex loads it when a task matches its description.
Can I use Agent Introspection 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 hashgraph-online/awesome-codex-plugins --skill agent-introspection -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agent-introspection, .gemini/skills/agent-introspection, .github/skills/agent-introspection and .opencode/skills/agent-introspection in your project.
What does Agent Introspection need to run?
SKILL.md names no scripts, command-line tools or credentials: Agent Introspection is instructions for the agent only.
Does Agent Introspection 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 Agent Introspection 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 Agent Introspection use?
Agent Introspection is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Agent Introspection use?
About 960 tokens (SKILL.md is roughly 3.8k 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 Agent Introspection?
Skills that share tags, products or a category with Agent Introspection: Agent Introspection Debugging (affaan-m/ECC, 276k stars), Dart Log Failure Parser (flutter/flutter, 179k stars), V5 Breaking Changes (remotion-dev/remotion, 63k stars) and Investigating CI Failures (PostHog/posthog, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Agent Introspection?
hashgraph-online (a GitHub organization) maintains it in hashgraph-online/awesome-codex-plugins, which has 1,255 GitHub stars. The repository holds 714 skills in this directory. The repository was last updated on October 9, 2026.
Source: hashgraph-online/awesome-codex-plugins on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.