bound-live-debugging

bound-live-debugging is a skill for Claude Code, Codex from karashiiro/agent-skills. It costs 37 tokens per session (1,279 once invoked), scanned A, original, Unlicense.

A procedure for investigating a running Bound agent, an instance that can hold conversations and store information. It combines conversations with database checks and test-driven development, or TDD, where a failing test guides the fix.

In plain words
What is it for?
It helps investigate command failures, missing context or memories, and unexpected behavior in a live agent. It covers probing through conversation, checking the database directly, applying a test-guided fix, and re-testing.
Why use it?
It helps distinguish stale conversation results from the agent's actual stored state and supports a repeatable cycle of finding, fixing, restarting, and checking problems.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/karashiiro/agent-skills/bound-live-debugging
Any agent
npx skills add karashiiro/agent-skills --skill bound-live-debugging
Clone the repo
git clone --depth 1 https://github.com/karashiiro/agent-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for bound-live-debugging

README.md
[![agentmods](https://agentmods.dev/badge/skills/karashiiro/agent-skills/bound-live-debugging.svg)](https://agentmods.dev/skills/karashiiro/agent-skills/bound-live-debugging)
Your own site
<a href="https://agentmods.dev/skills/karashiiro/agent-skills/bound-live-debugging"><img src="https://agentmods.dev/badge/skills/karashiiro/agent-skills/bound-live-debugging.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,279 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00037 $0.01279
Opus 5 $0.00018 $0.00639
Sonnet 5 $0.00007 $0.00256
Haiku 4.5 $0.00004 $0.00128

Measured 5d ago against content hash a542a7e7feb0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

bound-live-debugging scanned grade A with 1 finding 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 5d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s -X POST "http://localhost:3000/api/advisories/$ID/approve"
bound-live-debugging/SKILL.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Live Debugging a Bound Agent

Overview

Debug a running bound instance by combining direct database inspection, MCP-based agent conversations, and targeted TDD fix cycles. Core loop: probe via conversation, verify via DB, fix with TDD, restart and re-probe.

When to Use

  • Bound agent exhibiting unexpected behavior
  • Investigating command failures, context assembly issues, or memory gaps
  • Verifying fixes end-to-end against a live instance
  • Probing for undiscovered issues through open-ended agent interaction

Setup

Start bound from the data directory so config paths resolve:

cd ~/bound && bun /path/to/bound/packages/cli/src/bound.ts start 2>&1 &

Kill and restart after each code change. Bun runs TypeScript source directly.

Core Patterns

1. Conversation as Probe

Use bound_chat (Polaris MCP) to hold diagnostic conversations. The agent is itself a capable debugger — ask it to inspect its own state with query, memorize, forget, hostinfo, commands, advisory, skill-list.

2. DB as Ground Truth

bound_chat may return stale content from a previous turn (polling race). Always verify via direct DB query:

THREAD=$(sqlite3 ~/bound/data/bound.db "SELECT id FROM threads WHERE interface='mcp' ORDER BY created_at DESC LIMIT 1;")
sqlite3 ~/bound/data/bound.db "SELECT substr(content,1,1000) FROM messages WHERE thread_id='$THREAD' AND role='assistant' ORDER BY created_at DESC LIMIT 1;"

3. Schema Before Query

Always check .schema <table> before querying unfamiliar tables. Common traps: advisories.proposed_at (not created_at), tasks has no name column, turns.tokens_cache_write/tokens_cache_read (may be NULL).

4. Agent Self-Report

Ask open-ended questions about functioning. Agents notice real issues: "Event emitted: undefined" exposed a parsing bug. "purge requires --thread-id" exposed a singleton context gap. Watch for repeated analysis across conversations — signals missing cross-session memory.

Read the full file on GitHub · 122 lines

Changes

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.

  1. 5d ago First seen · 122 lines · 37 tokens per session scan A a542a7e7feb0

Subscribe to this mod's changes

bound-live-debugging is a skill published in the GitHub repository karashiiro/agent-skills (2 stars, last pushed 4mo ago), licensed Unlicense. It adds 37 tokens to every session and 1,279 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens