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 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/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<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="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00027 | $0.01388 |
| Opus 5.5 | $0.00011 | $0.00555 |
| Sonnet 5.5 | $0.00005 | $0.00278 |
| Haiku 4.5 | $0.00003 | $0.00139 |
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 28d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What I do
Systematically diagnose why agents, skills, or subagents misbehave: configuration validation → permission audit → context/behavior analysis → specific fix recommendations.
Trigger phrases: "debug agent", "why is the agent not working", "agent introspection", "skill not triggering", "agent ignoring instructions", "fix agent behavior", "diagnose subagent".
Step 1: Symptom → Likely Cause
| Symptom | Category | Likely Cause |
|---|---|---|
| Agent doesn't spawn | Config | Missing .md file, wrong name, permission issue |
| Spawns but does nothing | Permissions | Tools denied, no skill access, step limit too low |
| Wrong output | Behavior | Missing context, conflicting instructions, model limits |
| Ignores AGENTS.md | Routing | AGENTS.md not loaded, routing rules override |
| Skill doesn't trigger | Discovery | Name mismatch, trigger phrases missing, not installed |
| Can't use tools | Permissions | Tool not in permissions allowlist |
| Loops or repeats | Behavior | Missing termination condition, unclear success criteria |
| MCP tools not called | Discovery | Server not configured, tool unknown to agent |
Step 2: Configuration Checklist
Agent (agents/<name>.md): file exists · description present and <50 words (always in Task context) · mode set · model valid · steps set (10-25) · permissions rules array present (v2 shape) · YAML parses · body is valid markdown.
Skill (skills/<name>/SKILL.md): directory name == frontmatter name exactly · description present · license + compatibility present · required sections present ("What I do", "When to use me", workflow) · YAML parses.
Step 3: Permission Audit
For each needed tool: allowed in permissions? Any deny overriding it? task delegation targets allowed? For each loaded skill: allowed via action: skill rule? Directory exists with valid SKILL.md? Name case-exact?
| Issue | Symptom | Fix |
|---|---|---|
Missing read allow |
Can't read files | Add {action: read, effect: allow} |
Missing glob allow |
Can't find files | Add glob allow rule |
Missing subagent targets |
Can't spawn subagents | Allow the subagent names (action: subagent) |
edit: deny but must edit |
Reads, never modifies | Allow edit (scoped to task paths) |
shell: deny on build agent |
Can't run commands | Allow shell with caution |
| Skill name mismatch | Skill won't load | Match exact directory name |
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.
- 28d ago Changed · +2 lines a2d38afc6f8c
- 29d ago Changed fbd4fe18b389
- 1mo ago Changed · -196 lines df24ee45cc3a
- 1mo ago Changed 7c768dc015a8
- 1mo 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 28d ago), licensed Apache-2.0. It adds 27 tokens to every session and 1,388 once invoked, about $0.0001 per session on Opus 5.5. 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
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…
diagnose
Extract the learning signal from execution traces — the textual analogue of a gradient. Use between evaluation and proposing edits. Reads a candidate's rollouts and traces, separates good signals to keep from bad signals to fix, builds a reflective dataset (per failing task — Inputs, Generated Outputs, Feedback) and…
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
deck-retro
Run a fully local agent-deck retrospective over the user's own transcripts, Recall index and logs. Use when a user wants to find recurring failures or take their own finding from investigation through synthetic reproduction, a user-filed issue, a test-first fix and contributor PR handoff. Also use for weekly usage…