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 claude-world/director-mode-lite --skill debuggergit clone --depth 1 https://github.com/claude-world/director-mode-liteWrote 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/claude-world/director-mode-lite/debugger)<a href="https://agentmods.dev/skills/claude-world/director-mode-lite/debugger"><img src="https://agentmods.dev/badge/skills/claude-world/director-mode-lite/debugger/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/claude-world/director-mode-lite/debugger"><img src="https://agentmods.dev/badge/skills/claude-world/director-mode-lite/debugger.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 | $0.00056 | $0.00887 |
| Opus 5.5 | $0.00022 | $0.00355 |
| Sonnet 5.5 | $0.00011 | $0.00177 |
| Haiku 4.5 | $0.00006 | $0.00089 |
Grade A, and why
debugger 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 1mo 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debugger Skill
Director Mode Lite - Debugging Specialist
5-Step Root-Cause Method
1. CAPTURE → Collect the full error, reproduce, define expected vs actual
2. ISOLATE → Narrow to the smallest failing case
3. HYPOTHESIZE → List and rank likely causes
4. INVESTIGATE → Test hypotheses, inspect state
5. FIX & VERIFY → Apply the minimal fix, confirm, prevent recurrence
Step 1: Capture
- Collect the complete error message and stack trace
- Can reproduce the issue with clear steps
- Identify the input that triggered the error
- Know expected vs actual behavior
Step 2: Isolate
- Identify the failure location from the stack trace
- Which file(s) and function(s) are involved?
- When did it start? (
git bisect,git log) - Narrow down to the smallest reproducible case
Step 3: Hypothesize
- List possible causes based on evidence
- Rank hypotheses by likelihood
- Design a test to confirm or eliminate each
Step 4: Investigate
- Analyze error messages and logs carefully
- Add strategic debug logging; inspect variable state at key points
- Check for: null/undefined values, type mismatches, race conditions, resource exhaustion, external service failures
Common Bug Patterns
| Pattern | Signs | Common Fix |
|---|---|---|
| Null/Undefined | Cannot read property of undefined |
Add null checks / optional chaining |
| Off-by-one | Loop runs one too many/few times | Check loop bounds |
| Race condition | Intermittent failures | Add synchronization |
| Type coercion | "1" + 1 = "11" |
Explicit type conversion |
| Async issues | Promise { <pending> } |
Await/handle promises |
By language and domain:
- JavaScript/TypeScript:
undefined is not a function(binding),Cannot read property of null(optional chaining), promise rejections (async/await handling), type errors (strict mode) - Python:
AttributeError(init/typos),TypeError(type validation),ImportError(paths, circular imports),KeyError(dict defaults) - Database: connection timeouts (pool exhaustion), constraint violations (validation, foreign keys), deadlocks (transaction ordering)
- API/Network: 4xx (request validation, auth), 5xx (server-side, resource limits), timeouts (network, long-running queries)
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.
- 1mo ago Changed · -6 lines 09f3f50a8faf
- 1mo ago First seen · 125 lines · 56 tokens per session scan A 0eea01f7be8a
debugger is a skill published in the GitHub repository claude-world/director-mode-lite (80 stars, last pushed 1mo ago), licensed MIT. It adds 56 tokens to every session and 887 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
mobile-flows-maestro
This skill should be used when Maestro is explicitly requested or already present and the task is to author, run, or debug iOS/Android Maestro flows; use Maestro MCP; or handle Maestro selectors, system UI, permissions, Keychain, JavaScript, waits, device state, flakiness, or CI. Evidence includes a .maestro directory…
esp32-expert
This skill should be used for ESP32-specific hardware and runtime work in ESP-IDF, Arduino-ESP32, or PlatformIO projects: target/build detection, FreeRTOS tasks and ISRs, memory/DMA, peripherals, power, networking/security, OTA, crash diagnosis, and unattended reliability. Trigger on "debug this ESP32 crash", "review…
concise
Concise communication mode. Cuts 60-70% of output tokens while keeping natural, readable English. Drops filler, hedging, and pleasantries but maintains grammar and sentence flow. Elaborate on request -- ask for detail and get it, then auto-return to concise. Use when user says "concise mode", "be concise", "less…
debug-extension
Diagnose and fix failures in a built third-party .ppmplugin control: crashes, silent no-ops, PCF error outputs, or incorrect behavior. Uses the reported symptom, shared/error-codes.md, and file-level evidence to trace the manifest, Android/iOS modules, PCF dispatch, and build configuration. Produces a ranked…
audit-ppmplugin
Statically audit a built .ppmplugin before wrap testing. Checks archive layout, manifest compatibility, bundle consistency, Android DEX integrity and SDK leakage, iOS framework structure, native source-to-receiver alignment, and the PCF composite-key/sendAsync transport contract. Reports CRITICAL, WARNING, and INFO…
diagnose-flow
Deep autonomous diagnosis of a failed flow run. Provide environment, flow, and run IDs. Use when the user asks to diagnose or deeply investigate a specific failed flow run.