AI DevKit is a local-first control layer that gives multiple AI coding agents shared configuration, a terminal dashboard, cross-agent messaging, local memory retrieval, and reusable engineering workflows. It is for developers and teams supervising agents such as Claude Code, Codex CLI, Gemini CLI, OpenCode, Pi, Cursor, Copilot, or Devin. The catalogue entries are composable skills and plugin components used within that agent-management system.
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 codeaholicguy/ai-devkit --skill dev-debuggit clone --depth 1 https://github.com/codeaholicguy/ai-devkitWrote 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/codeaholicguy/ai-devkit/dev-debug)<a href="https://agentmods.dev/skills/codeaholicguy/ai-devkit/dev-debug"><img src="https://agentmods.dev/badge/skills/codeaholicguy/ai-devkit/dev-debug/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/codeaholicguy/ai-devkit/dev-debug"><img src="https://agentmods.dev/badge/skills/codeaholicguy/ai-devkit/dev-debug.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00079 | $0.00624 |
| Opus 5.5 | $0.00032 | $0.00250 |
| Sonnet 5.5 | $0.00016 | $0.00125 |
| Haiku 4.5 | $0.00008 | $0.00062 |
Grade A, and why
dev-debug 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 4d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Local Debugging Assistant
Debug with an evidence-first workflow before changing code.
Hard Rule
- Do not modify code until the user approves a selected fix plan.
Workflow
- Clarify
- Restate observed vs expected behavior in one concise diff.
- Confirm scope and measurable success criteria.
- Before investigating, search for similar past incidents:
npx ai-devkit@latest memory search --query "<observed behavior>" --tags "debug,root-cause"
- Reproduce
- Capture minimal reproduction steps. For user-flow bugs, make the repro a
dev-smokecheck that fails before the fix and passes after. - Capture environment fingerprint: runtime, versions, config flags, data sample, and platform.
- Hypothesize and Test For each hypothesis, include:
- Predicted evidence if true.
- Disconfirming evidence if false.
- Exact test command or check.
- Prefer one-variable-at-a-time tests.
- Plan
- Present fix options with risks and verification steps.
- Recommend one option and request approval.
Validation
- Confirm a pre-fix failing signal exists.
- Confirm post-fix success using the
verifyskill — including regression verification for bug fixes. - Summarize remaining risks and follow-ups.
- Offer
dev-retroto prevent recurrence; run only if the user agrees. - Store root cause and fix for future sessions:
npx ai-devkit@latest memory store --title "<root cause>" --content "<diagnosis and fix>" --tags "debug,root-cause"
Task Tracing
If task tracing is usable, choose a short kebab-case debug task name when no
task name exists, then use task optionally: record repro/final results as
evidence, the current hypothesis as next, and blockers only when they
materially affect progress. Never block debugging because task tracing is
unavailable.
Red Flags and Rationalizations
| Rationalization | Why It's Wrong | Do Instead |
|---|---|---|
| "I already know the cause" | Assumptions skip evidence | Reproduce and prove it first |
| "This is urgent, just fix it" | A wrong fix wastes more time | 10 minutes of diagnosis saves hours |
| "The fix is obvious from the stack trace" | Stack traces show symptoms, not causes | Trace backward to the root cause |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 66 lines · 79 tokens per session scan A abdbd8562d64
dev-debug is a skill published in the GitHub repository codeaholicguy/ai-devkit (1,654 stars, last pushed 2d ago), licensed Apache-2.0. It adds 79 tokens to every session and 624 once invoked, about $0.0003 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 2026-10-24.
Other skills, from other repositories
doubt-driven-development
Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when you want every assumption cross-examined before proceeding, when stress-testing a plan for hidden failure modes, when correctness matters more than speed, when working in unfamiliar code, when stakes are high…
performance-optimization
Optimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect performance regressions, when Core Web Vitals or load times need improvement, when N+1 query patterns need fixing, or when profiling reveals bottlenecks.
api-integration-architect
Design, implement, debug, and optimize API integrations with expert-level patterns for REST, GraphQL, webhooks, and authentication flows.
agenttrace-session-audit
Audit local AI coding-agent sessions with agenttrace for cost, tool failures, latency, anomalies, health, diffs, and CI gates.
accesslint-scan
Audit a live page for accessibility issues, locate each WCAG violation precisely, and return a selector-grounded fix worklist without editing.
agent-qa-result-triage
Triage failed Agent QA runs with MCP evidence, artifacts, logs, fixed failure categories, confidence, and actionable next steps.