New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Bridge Agent Log Analyzer

by AFK-surf in AFK-surf/OpenBridge

Analyze Bridge agent execution logs from ~/.bridge/sessions, reconstruct the agent's actual runtime behavior, and explain tool execution, failures, retries, and artifacts from persisted session files.

MITAuto-check passed

Install Bridge Agent Log Analyzer

skills CLI
$ npx skills add AFK-surf/OpenBridge --skill bridge-agent-log-analyzer -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install AFK-surf/OpenBridge bridge-agent-log-analyzer --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/AFK-surf/OpenBridge.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/bridge-agent-log-analyzer .claude/skills/bridge-agent-log-analyzer && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
bridge-agent-log-analyzer
GitHub stars
430
Token cost
~1.3k tokens
SKILL.md length
564 words
Files
4 (incl. scripts, references)
Skills in repo
14
Repo updated
First seen
Licence
MIT

At a glance

Analyze Bridge agent execution logs from ~/.bridge/sessions, reconstruct the agent's actual runtime behavior, and explain tool execution, failures, retries, and artifacts from persisted session files.

  • Works in 5 steps: Identify the target session or log… → Run scripts/inspect_bridge_session.py… → Read only the raw files needed to… → …
  • SKILL.md covers Overview, Default Workflow, Quick Start and Primary Evidence Sources, plus 5 more sections
  • Runs Python scripts from its folder; calls python3

What it does

Bridge Agent Log Analyzer is an agent skill from AFK-surf/OpenBridge. Analyze Bridge agent execution logs from ~/.bridge/sessions, reconstruct the agent's actual runtime behavior, and explain tool execution, failures, retries, and artifacts from persisted session files.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts and reference files (for example `agents/openai.yaml`, `references/log-sources.md` and `scripts/inspect_bridge_session.py`).

The repository describes itself as: A free, safe and open agent for everything. Alternative to Claude Cowork & Codex. Open Bridge, the AI bridge between your intention and get the job done. The licence is MIT.

Example prompts

  • “/bridge-agent-log-analyzer”

Requirements

  • Python 3

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Identify the target session or log identifier.
  2. Run scripts/inspect_bridge_session.py first.
  3. Read only the raw files needed to explain the behavior
  4. Reconstruct the execution chronologically.
  5. Separate direct evidence from inference.

What it can do on your machine

Read from SKILL.md and the folder at commit a9ca905. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Bridge Agent Log Analyzer loads about 1.3k tokens when it runs, and up to ~1.8k if it reads all its reference files. Until then it costs about 57 tokens; SKILL.md has 564 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~57
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from AFK-surf/OpenBridge at commit a9ca905, republished under its MIT licence (© AFK-surf). 564 words, ~1,259 tokens.

Download SKILL.mdSave it as .claude/skills/bridge-agent-log-analyzer/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
bridge-agent-log-analyzer
description
Analyze Bridge agent execution logs from ~/.bridge/sessions, reconstruct the agent's actual runtime behavior, and explain tool execution, failures, retries, and artifacts from persisted session files.

Bridge Agent Log Analyzer

Overview

Inspect one persisted Bridge session and turn its on-disk logs into a behavior report.

This skill is for analyzing the agent itself:

  • what it tried to do
  • which tools it called
  • which calls ran in the background
  • where it failed
  • how it recovered or retried
  • which artifacts it read or produced

This skill is not for UI reconstruction. Ignore frontend display behavior unless the user explicitly asks for it.

Default Workflow

  1. Identify the target session or log identifier.
  2. Run scripts/inspect_bridge_session.py first.
  3. Read only the raw files needed to explain the behavior:
    • session-meta.json
    • agent/history.json
    • agent/context.json
    • agent/state.json
    • agent/toolcalls/*/meta.json
    • agent/toolcalls/*/output.log
    • subagent equivalents under agents/<subagent-id>/agent/
  4. Reconstruct the execution chronologically.
  5. Separate direct evidence from inference.

Quick Start

Inspect the most recent session:

bash
python3 .agents/skills/bridge-agent-log-analyzer/scripts/inspect_bridge_session.py

Inspect a specific session directory ID:

bash
python3 .agents/skills/bridge-agent-log-analyzer/scripts/inspect_bridge_session.py --session-id <session-id>

Inspect using any UUID or identifier that appears inside that session's logs:

bash
python3 .agents/skills/bridge-agent-log-analyzer/scripts/inspect_bridge_session.py --session-id <message-or-toolcall-id>

The helper script is the index. Use it to find the real session directory, runtime toolcalls, failures, and likely recovery paths before opening raw files.

Primary Evidence Sources

  • history.json
    • user-visible messages and task state transitions
  • context.json
    • assistant decision points, tool calls, and tool results
  • toolcalls/*/meta.json
    • runtime command, async promotion, exit code, timing, environment
  • toolcalls/*/output.log
    • actual command output, error text, tracebacks, downloads, progress
  • state.json
    • model, reasoning effort, last-round token and step summary
  • session-meta.json
    • session title, environments, created/updated timestamps

Use workspace files only when the agent explicitly read or referenced them in logs.

What To Extract

Session overview
  • real session directory ID
  • whether the requested identifier was a direct session ID or a reverse lookup hit
  • environment labels
  • effective start/end time based on history and toolcall timestamps
Behavior timeline

Use context.json as the main execution timeline.

  • one assistant message is one decision point
  • assistant content is a visible reply or intermediate narration
  • assistant tool_calls are intended actions
  • later tool messages are immediate tool results
  • toolcalls/* supplies runtime metadata for those tool calls
Tool execution

Summarize:

  • tool name
  • order of invocation
  • arguments or command preview
  • runtime status
  • sync vs async/background execution
  • exit code
  • duration
  • output preview
Show full SKILL.md (226 more words)Show less
Failures and recovery

Focus on:

  • failed toolcalls
  • error-like tool results
  • retries of the same tool
  • diagnostics between a failure and a retry
  • mismatches between summary files and raw logs
Artifacts and final state

Extract:

  • files the agent explicitly read
  • result files written and later inspected
  • final kept state when the logs make it clear
Skill evidence

Only mention skill usage when there is concrete evidence such as:

  • a tool opening a SKILL.md
  • a command explicitly targeting a skill path

Report this as inferred skill usage.

Privacy Boundary

Do not output agent thinking.

  • ignore reasoning
  • ignore encrypted_reasoning
  • do not decode or summarize hidden reasoning

This skill explains behavior from logs, not hidden chain-of-thought.

Reporting Format

Default to a concise Markdown report with:

  1. Session overview
  2. Behavior timeline
  3. Tool execution summary
  4. Failures and recovery
  5. Artifacts and final state
  6. Inferred skill usage
  7. Gaps and uncertainty

For each important step, include:

  • trigger or input
  • assistant action
  • tools called
  • outcome
  • evidence source

Failure Modes

  • Missing history.json: rely on context.json, toolcalls/*, and state.json
  • Missing context.json: restrict to user-visible history plus runtime toolcalls if present
  • Missing toolcalls/*: fall back to context.json tool results
  • Missing tool result for a tool_call_id: report it as unmatched, not failed
  • Sessions with subagents: analyze each agent separately, then combine

Resources

  • scripts/inspect_bridge_session.py
    • behavior-focused summary for one session
  • references/log-sources.md
    • artifact map and evidence grading

© AFK-surf, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (scripts, references) in .agents/skills/bridge-agent-log-analyzer of AFK-surf/OpenBridge.

  • SKILL.md
  • agents/openai.yaml
  • references/log-sources.md
  • scripts/inspect_bridge_session.py

Open the folder on GitHubat commit a9ca905

Compare with similar skills

Bridge Agent Log Analyzer next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Bridge Agent Log Analyzer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Bridge Agent Log Analyzer this skillAFK-surf/OpenBridge430—~1.3kAutomated safety check: PassMIT
Analyze Logsactivepieces/activepieces25k1 repos~1.6kAutomated safety check: PassMIT
Analyzing Experiment Session ReplaysPostHog/posthog40k—~2.4kAutomated safety check: PassCustom licence
Analyzing Security Logs With Splunkmukul975/Anthropic-Cybersecurity-Skills34k—~2.5kAutomated safety check: PassApache-2.0
Analyzing DNS Logs For Exfiltrationmukul975/Anthropic-Cybersecurity-Skills34k—~2.9kAutomated safety check: PassApache-2.0
Analyze GitHub Action Logswithastro/astro63k1 repos~1.3kAutomated safety check: PassCustom licence

Similar skills

  • Analyze Logs

    activepieces/activepieces

    Analyze application logs from the .evlog/logs/ directory. An agent skill from activepieces/activepieces.

    25k GitHub starsUsed in 1 repo~1.6k tokens
    DevelopmentAuto-check passed

  • Analyzing Experiment Session Replays

    PostHog/posthog

    Official

    Analyze session replay patterns across experiment variants to understand user behavior differences.

    40k GitHub stars~2.4k tokensUpdated today
    Frontend & DesignAuto-check passed

  • Analyzing Security Logs With Splunk

    mukul975/Anthropic-Cybersecurity-Skills

    Leverages Splunk Enterprise Security and SPL (Search Processing Language) to investigate security incidents through log correlation, timeline reconstruction, and anomaly detection.

    34k GitHub stars~2.5k tokensUpdated 1 mo ago
    SecurityAuto-check passed

  • Analyzing DNS Logs For Exfiltration

    mukul975/Anthropic-Cybersecurity-Skills

    Analyzes DNS query logs to detect data exfiltration via DNS tunneling, DGA domain communication, and covert C2 channels using entropy analysis, query volume anomalies, and subdomain length detection…

    34k GitHub stars~2.9k tokensUpdated 1 mo ago
    SecurityAuto-check passed

  • Analyze GitHub Action Logs

    withastro/astro

    Official

    Analyze recent GitHub Actions workflow runs to identify patterns, mistakes, and improvements.

    63k GitHub starsUsed in 1 repo~1.3k tokens
    DevOps & CloudAuto-check passed

  • Analyzing Windows Event Logs In Splunk

    mukul975/Anthropic-Cybersecurity-Skills

    Analyzes Windows Security, System, and Sysmon event logs in Splunk to detect authentication attacks, privilege escalation, persistence mechanisms, and lateral movement using SPL queries mapped to…

    34k GitHub stars~2.8k tokensUpdated 1 mo ago
    SecurityAuto-check passed

More from AFK-surf/OpenBridge

All 14 skills in this repo

  • Swiftui UI Patterns

    AFK-surf/OpenBridge

    Best practices and example-driven guidance for building SwiftUI views and components.

    430 GitHub starsUsed in 4 repos~887 tokens
    Auto-check passed

  • Swiftui Expert Skill

    AFK-surf/OpenBridge

    Write, review, or improve SwiftUI code following best practices for state management, view composition, performance, modern APIs, Swift concurrency, and iOS 26+ Liquid Glass adoption.

    430 GitHub starsUsed in 2 repos~3.9k tokens
    Auto-check passed

  • UI Designer

    AFK-surf/OpenBridge

    Design or restyle user interfaces using vendored DESIGN.md references from popular product and brand-inspired visual systems.

    430 GitHub stars~4.6k tokensUpdated 4 mo ago
    Auto-check passed

  • Format Converter

    AFK-surf/OpenBridge

    Convert files between formats. An agent skill from AFK-surf/OpenBridge.

    430 GitHub stars~549 tokensUpdated 4 mo ago
    Auto-check passed

  • Skill Manager

    AFK-surf/OpenBridge

    Manage skills: create, install, modify, or delete skills. An agent skill from AFK-surf/OpenBridge.

    430 GitHub stars~749 tokensUpdated 4 mo ago
    Auto-check passed

  • Swift Concurrency

    AFK-surf/OpenBridge

    Expert guidance on Swift Concurrency best practices, patterns, and implementation.

    430 GitHub stars~2.8k tokensUpdated 4 mo ago
    Auto-check passed

Questions about Bridge Agent Log Analyzer

What does Bridge Agent Log Analyzer do?

Analyze Bridge agent execution logs from ~/.bridge/sessions, reconstruct the agent's actual runtime behavior, and explain tool execution, failures, retries, and artifacts from persisted session files. Bridge Agent Log Analyzer is an agent skill from AFK-surf/OpenBridge.bridge/sessions, reconstruct the agent's actual runtime behavior, and explain tool execution, failures, retries, and artifacts from persisted session files.

How do I install Bridge Agent Log Analyzer in Claude Code?

Run `npx skills add AFK-surf/OpenBridge --skill bridge-agent-log-analyzer -a claude-code`. Or copy the skill folder (.agents/skills/bridge-agent-log-analyzer in AFK-surf/OpenBridge) into .claude/skills/bridge-agent-log-analyzer in your project. Claude Code loads it when a task matches its description.

How do I install Bridge Agent Log Analyzer in Codex?

Run `npx skills add AFK-surf/OpenBridge --skill bridge-agent-log-analyzer -a codex`. Or copy the skill folder (.agents/skills/bridge-agent-log-analyzer in AFK-surf/OpenBridge) into .agents/skills/bridge-agent-log-analyzer in your project. Codex loads it when a task matches its description.

Can I use Bridge Agent Log Analyzer in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add AFK-surf/OpenBridge --skill bridge-agent-log-analyzer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/bridge-agent-log-analyzer, .gemini/skills/bridge-agent-log-analyzer, .github/skills/bridge-agent-log-analyzer and .opencode/skills/bridge-agent-log-analyzer in your project.

What does Bridge Agent Log Analyzer need to run?

Going by SKILL.md and its folder, Bridge Agent Log Analyzer needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Bridge Agent Log Analyzer access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Bridge Agent Log Analyzer safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Bridge Agent Log Analyzer use?

Bridge Agent Log Analyzer is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Bridge Agent Log Analyzer use?

About 1.3k tokens (SKILL.md is roughly 5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 551 tokens, read only when the agent opens those files.

What are the alternatives to Bridge Agent Log Analyzer?

Skills that share tags, products or a category with Bridge Agent Log Analyzer: Analyze Logs (activepieces/activepieces, 25k stars), Analyzing Experiment Session Replays (PostHog/posthog, 40k stars), Analyzing Security Logs With Splunk (mukul975/Anthropic-Cybersecurity-Skills, 34k stars) and Analyzing DNS Logs For Exfiltration (mukul975/Anthropic-Cybersecurity-Skills, 34k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Bridge Agent Log Analyzer?

AFK-surf (a GitHub organization) maintains it in AFK-surf/OpenBridge, which has 430 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on June 10, 2026.

Source: AFK-surf/OpenBridge on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.