Borrowing it
Nothing to install: this file belongs to ai-debugger-inc/aidb. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ai-debugger-inc/aidb/main/.claude/skills/dap-protocol-guide/SKILL.mdgit clone --depth 1 https://github.com/ai-debugger-inc/aidbWrote 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/ai-debugger-inc/aidb/dap-protocol-guide)<a href="https://agentmods.dev/skills/ai-debugger-inc/aidb/dap-protocol-guide"><img src="https://agentmods.dev/badge/skills/ai-debugger-inc/aidb/dap-protocol-guide/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/ai-debugger-inc/aidb/dap-protocol-guide"><img src="https://agentmods.dev/badge/skills/ai-debugger-inc/aidb/dap-protocol-guide.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 | $0.00018 | $0.03355 |
| Opus 5.5 | $0.00007 | $0.01342 |
| Sonnet 5.5 | $0.00004 | $0.00671 |
| Haiku 4.5 | $0.00002 | $0.00335 |
Grade A, and why
dap-protocol-guide 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 2mo 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 — 495 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DAP Protocol Guide for AIDB
This skill provides comprehensive guidance for working with the Debug Adapter Protocol (DAP) in AIDB. Use this when implementing features that interact with debug adapters, analyzing DAP message flows, or troubleshooting protocol-level issues.
Overview
The Debug Adapter Protocol (DAP) is a standardized protocol for communication between development tools and debug adapters. AIDB provides a fully-typed, authoritative implementation in src/aidb/dap/protocol/.
For system-wide DAP architecture, see docs/developer-guide/overview.md which includes:
- Complete data flow diagrams
- DAP client layer details
- Integration with adapters and session management
Key Principles
- Always use existing protocol types - Don't create dictionaries manually
- Follow established patterns - Check adapter implementations before creating new request sequences
- Handle errors properly - DAP has specific error response patterns
- Respect initialization sequence - Initialize → Launch/Attach → ConfigurationDone
- Consider language differences - Python, JavaScript, and Java adapters have different behaviors
Authoritative Source
src/aidb/dap/protocol/ is THE authoritative reference for all DAP types and messages.
This package contains:
types.py- DAP data types (Breakpoint, StackFrame, Variable, etc.)requests.py- All request message classesresponses.py- All response message classesevents.py- All event message classesbodies.py- Request arguments and response bodiesbase.py- Base classes (Request, Response, Event, ProtocolMessage)
Quick Reference
Common DAP Operations
# Import protocol types
from aidb.dap.protocol import (
InitializeRequest,
LaunchRequest,
SetBreakpointsRequest,
StackTraceRequest,
ScopesRequest,
VariablesRequest,
ContinueRequest,
)
from aidb.dap.protocol.types import Source, SourceBreakpoint
from aidb.dap.protocol.bodies import (
InitializeRequestArguments,
LaunchRequestArguments,
SetBreakpointsArguments,
StackTraceArguments,
)
# Get next sequence number
seq = await client.get_next_seq()
# Build a request
request = SetBreakpointsRequest(
seq=seq,
arguments=SetBreakpointsArguments(
source=Source(path="/path/to/file.py"),
breakpoints=[
SourceBreakpoint(line=10, condition="x > 5")
]
)
)
# Send request and await response
response = await client.send_request(request)
What ships with it
6 files 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.
- 2mo ago First seen · 495 lines · 18 tokens per session scan A 5bee8dcb44a6
dap-protocol-guide is a skill published in the GitHub repository ai-debugger-inc/aidb (21 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 18 tokens to every session and 3,355 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 2026-08-30.
dap-protocol-guide compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| dap-protocol-guideai-debugger-inc/aidb | Skill | 21 | 5mo ago | Apache-2.0 | A | 18 | Claude Code |
| iterate-implementationhumanlayer/humanlayer | Skill | 13k | yesterday | Apache-2.0 | A | 16 | Claude Code, Codex |
| neuron-monitoringneuron-core/neuron-ai | Skill | 2.2k | yesterday | MIT | A | 80 | Claude Code, Codex |
| Detrix Dynamic Observabilityflashus/detrix | Skill | 29 | 2mo ago | MIT | A | 82 | Claude Code, Codex |
| bugfix-protocolellmos-ai/skills | Skill | 9 | 4d ago | MIT | C | 34 | Claude Code, Codex |
| Debugium DAP DebuggerAlgiras/debugium | Skill | 4 | 7mo ago | none | A | 67 | Claude Code |
| systematic-debuggingNousResearch/hermes-agent | Skill | 261k | yesterday | MIT | A | 16 | Claude Code, Codex |