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/jstoup111/ai-conductor/debuggingnpx skills add jstoup111/ai-conductor --skill debugginggit clone --depth 1 https://github.com/jstoup111/ai-conductorWhat 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 | $0.00048 | $0.01594 |
| Opus 5 | $0.00024 | $0.00797 |
| Sonnet 5 | $0.00010 | $0.00319 |
| Haiku 4.5 | $0.00005 | $0.00159 |
Grade A, and why
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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Prevents shotgun debugging by enforcing systematic root cause investigation before any fix is attempted. Evidence-based diagnosis catches the real problem instead of treating symptoms.
Correctness gate: a root-cause theory is a claim. Per the /verify-claims protocol, state it
with a grounded confidence % and its basis, and do not fix on it until the evidence puts it high —
a plausible-but-unverified theory produces a band-aid, not a fix.
Practices
Phase 1: Investigate
GATE: No fix proposals until investigation is complete.
-
Read the error. Fully. Not just the first line — the full stack trace, log output, and context.
-
Reproduce. Can you make it happen reliably?
- If yes: note the exact reproduction steps
- If intermittent: note the conditions under which it occurs and doesn't occur
-
Recall related memory. Before investigating further:
- Search
.memory/gotchas/for entries related to the error message, affected files, or domain area - Search
.memory/patterns/for entries about how similar code paths work - If a relevant gotcha exists, test it as your first hypothesis
- Search
-
Check what changed. What's different from when it last worked?
git log --oneline -10— recent commitsgit diff— uncommitted changes- Environment changes (new dependency versions, config changes)
-
Gather evidence. Before forming theories:
- Read the failing code path line by line
- Add temporary logging/debugging output at key points
- Check input data — is it what you expect?
- Check database state — are records in the expected state?
- If tech-context loaded: use stack-specific tools (e.g.,
rails console,binding.pry)
Phase 2: Pattern Analysis
-
Find a working example. Is there similar code that works correctly?
- Compare the working and broken versions
- What's different?
-
Check for known patterns. Cross-reference findings with
.memory/gotchas/recalled in step 3.
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 · 149 lines · 48 tokens per session scan A 01d49750f8a5
debugging is a skill published in the GitHub repository jstoup111/ai-conductor (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 48 tokens to every session and 1,594 once invoked, about $0.0002 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…