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/teammanagementplugin/claude-plugin/team-management-debuggingnpx skills add TeamManagementPlugin/claude-plugin --skill team-management-debugginggit clone --depth 1 https://github.com/TeamManagementPlugin/claude-pluginWhat 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 | $0.00095 | $0.01739 |
| Opus 5 | $0.00048 | $0.00870 |
| Sonnet 5 | $0.00019 | $0.00348 |
| Haiku 4.5 | $0.00010 | $0.00174 |
Grade A, and why
team-management-debugging 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 2d 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debugging Discipline
Core Principle
Find the root cause, not a symptom that quiets the error message. Random patches waste time and seed new bugs in adjacent code.
When to Use
Any technical issue: test failure, production bug, unexpected behaviour, performance regression, build failure, integration glitch. Especially under time pressure — systematic debugging is faster than guess-and-check, not slower.
Four-Phase Methodology
Phase 1 — Root-cause investigation
Complete this phase before proposing any fix.
-
Read the error carefully. Stack traces, line numbers, error codes. The solution is frequently stated in the message itself.
-
Reproduce consistently. What are the exact steps? Every time, or intermittently? If you cannot reproduce it, gather more data — do not guess.
-
Check recent changes.
git log,git diff, dependency bumps, config changes, and the environmental differences between where it works and where it fails. -
Instrument at component boundaries. For each boundary in the chain (CI → build → signing; API → service → database; client → proxy → worker), log what enters and what exits. Run once with instrumentation, read the evidence, then investigate the specific layer that failed. This tells you where the break is before you speculate about why.
# Layer 1: Workflow echo "IDENTITY: ${IDENTITY:+SET}${IDENTITY:-UNSET}" # Layer 2: Build script env | grep IDENTITY || echo "IDENTITY not in environment" # Layer 3: Signing security find-identity -v -
Trace the bad value backward. When the error surfaces deep in the stack, walk up: where does the bad value originate? What called this with it? Keep tracing until you reach the source, and fix it there — not at the symptom site.
Phase 2 — Pattern analysis
- Find working code that does something similar in the same codebase.
- If you are implementing an external pattern, read the reference implementation completely. Do not skim it.
- List every difference between the working example and the broken code, however small. "That can't matter" is a reliable source of bugs.
- Understand what the code depends on: config, environment, state, ordering.
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.
- 2d ago First seen · 169 lines · 95 tokens per session scan A 39182c8946d8
team-management-debugging is a skill published in the GitHub repository TeamManagementPlugin/claude-plugin (4 stars, last pushed 26d ago), licensed MIT. It adds 95 tokens to every session and 1,739 once invoked, about $0.0005 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
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
ideogram-ultra
Build Ideogram 4 (Ideogram Ultra) txt2img and img2img workflows with the local open-weights model, dual conditional/unconditional models with DualModelGuider, Qwen3-VL text encoder, and structured JSON ("compositional deconstruction") prompts for strong text rendering and layout control.
model-compatibility
Model family compatibility matrix covering loaders, resolutions, samplers, CFG, VAE, ControlNet, and LoRA compatibility for SD 1.5, SDXL, Flux, SD3, and video models.
flux-txt2img
Build Flux txt2img workflows with Flux.1 Dev (SRPO), Flux 2 Klein 9B, Turbo LoRAs, FluxGuidance, and DualCLIPLoader patterns.
openlore-brainstorm
Transform a feature idea into an annotated story using a Domain Sketch or Constrained Option Tree. Use when asked to brainstorm, explore, or shape a feature before implementation.