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.
npx agentmods add skills/darellchua2/opencode-config-template/agent-introspection-debugging-skillnpx skills add darellchua2/opencode-config-template --skill agent-introspection-debugging-skillgit clone --depth 1 https://github.com/darellchua2/opencode-config-templateWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/darellchua2/opencode-config-template/agent-introspection-debugging-skill)<a href="https://agentmods.dev/skills/darellchua2/opencode-config-template/agent-introspection-debugging-skill"><img src="https://agentmods.dev/badge/skills/darellchua2/opencode-config-template/agent-introspection-debugging-skill.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00027 | $0.02629 |
| Opus 5 | $0.00014 | $0.01314 |
| Sonnet 5 | $0.00005 | $0.00526 |
| Haiku 4.5 | $0.00003 | $0.00263 |
Grade A, and why
agent-introspection-debugging-skill 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 3d ago.
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.
How it starts
The opening of the file, as written. The whole thing — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What I do
I systematically diagnose why agents, skills, or subagents aren't producing expected output:
- Configuration Validation: Verify agent/skill files are correctly formatted and loadable
- Permission Auditing: Check tool access permissions match the agent's needs
- Context Analysis: Identify context-related issues (too much, too little, missing references)
- Behavioral Diagnosis: Trace why an agent makes unexpected decisions
- Fix Recommendations: Provide specific, actionable fixes for diagnosed issues
When to use me
Use this skill when:
- An agent or subagent produces unexpected or wrong output
- A skill doesn't trigger when it should
- A subagent fails to use tools you expected it to use
- An agent ignores instructions from AGENTS.md or its own .md file
- An MCP tool isn't being called when it should be
- You want to understand why an agent chose a particular approach
- A skill loads but its workflow isn't being followed
Trigger phrases:
- "debug agent"
- "why is the agent not working"
- "agent introspection"
- "skill not triggering"
- "agent ignoring instructions"
- "fix agent behavior"
- "diagnose subagent"
Core Workflow
Step 1: Identify the Problem
Clarify what's wrong:
| Symptom | Category | Likely Cause |
|---|---|---|
| Agent doesn't spawn | Config | Missing .md file, wrong name, permission issue |
| Agent spawns but does nothing | Permissions | Tools denied, no skill access, step limit too low |
| Agent produces wrong output | Behavior | Missing context, conflicting instructions, model limitations |
| Agent ignores AGENTS.md | Routing | AGENTS.md not loaded, routing rules override |
| Skill doesn't trigger | Discovery | Skill name mismatch, trigger not matched, skill not installed |
| Agent can't use tools | Permissions | Tool not in permission allowlist |
| Agent loops or repeats | Behavior | Missing termination condition, unclear task prompt |
| MCP tools not called | Discovery | MCP server not configured, tool name unknown to agent |
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.
- 3d ago First seen · 295 lines · 27 tokens per session scan A ae288dc6cefe
agent-introspection-debugging-skill is a skill published in the GitHub repository darellchua2/opencode-config-template (6 stars, last pushed 2d ago), licensed Apache-2.0. It adds 27 tokens to every session and 2,629 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 2026-08-31.
Other skills, from other repositories
HTML sang Webcake
Chuyển trang HTML thành file .pke mở được trong trình dựng Webcake, giữ đúng màu, cỡ chữ, ảnh và bố cục của bản gốc.
Javis Builder
Tạo hoặc sửa năng lực của Javis: agent, skill, workflow, loop, plugin. Kèm mẫu file chuẩn và luật chống trùng.
Ingest Source
Tiêu hoá một source thô vào Second Brain, chưng cất thành tri thức wiki tích luỹ.
Notes
Lưu tin nhắn hiện tại nguyên văn vào sources/ (kèm ảnh), tự chưng cất lên wiki nếu note đáng.
agent-optimize
Free-form optimization algorithm for agent orchestration mode: the conversational agent owns the whole search — proposing capability edits itself, screening them cheaply, gating each on full val, and sealing test once. Use when orchestrationmode is agent and algorithmskill is agent-optimize. For a deterministic loop…
tools
Optimize an agent's OWN tool surface (tools it implements, not an external MCP server). Use when the agent mis-selects tools, fills arguments wrong, calls the same tool N times in a row, or has a confusing, redundant, or oversized toolset. Covers tool names and descriptions, parameter docs, tool schemas, handler code…