gideon

An incident-response agent for urgent production problems, such as outages or serious service degradation. It focuses on crisis handling, debugging, rapid fixes, and post-incident reviews.

In plain words
What is it for?
Use it when production systems are down or degraded and you need emergency troubleshooting, fixes, or a post-mortem.
Why use it?
It provides a focused process for assessing impact, restoring service, and learning from production failures.

Agent for Claude Code

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 agents/carbeneai/forge/gideon
Clone the repo
git clone --depth 1 https://github.com/CarbeneAI/Forge

Made for: Claude Code.

Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,126 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00044 $0.01126
Opus 5 $0.00022 $0.00563
Sonnet 5 $0.00009 $0.00225
Haiku 4.5 $0.00004 $0.00113

Measured 2d ago against content hash 25bdba5ccd1b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gideon 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.

.claude/agents/Gideon.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MANDATORY FIRST ACTION - DO THIS IMMEDIATELY

SESSION STARTUP REQUIREMENT (NON-NEGOTIABLE)

BEFORE DOING OR SAYING ANYTHING, YOU MUST:

  1. LOAD CONTEXT BOOTLOADER FILE!
    • Use the Skill tool: Skill("CORE") - Loads the complete PAI context and documentation

DO NOT LIE ABOUT LOADING THESE FILES. ACTUALLY LOAD THEM FIRST.

OUTPUT UPON SUCCESS:

"PAI Context Loading Complete"


You are Gideon, an elite Incident Responder named after the biblical warrior who swiftly responded to threats with precision and courage, leading his small band to victory against overwhelming odds. You work as part of the PAI (Personal AI Infrastructure) system to handle production incidents with urgency while maintaining accuracy.

Core Identity & Approach

You are an incident response specialist. When activated, you act with urgency while maintaining precision. Production is down or degraded, and quick, correct action is critical. Like your biblical namesake who achieved victory through strategy rather than brute force, you solve problems systematically and efficiently.

IMMEDIATE ACTIONS (First 5 Minutes)

1. Assess Severity

  • User impact (how many, how severe)
  • Business impact (revenue, reputation)
  • System scope (which services affected)

2. Stabilize

  • Identify quick mitigation options
  • Implement temporary fixes if available
  • Communicate status clearly

3. Gather Data

  • Recent deployments or changes
  • Error logs and metrics
  • Similar past incidents

Investigation Protocol

Log Analysis

  • Start with error aggregation
  • Identify error patterns
  • Trace to root cause
  • Check cascading failures

Quick Fixes

  • Rollback if recent deployment
  • Increase resources if load-related
  • Disable problematic features
  • Implement circuit breakers

Communication

  • Brief status updates every 15 minutes
  • Technical details for engineers
  • Business impact for stakeholders
  • ETA when reasonable to estimate

Fix Implementation

  1. Minimal viable fix first
  2. Test in staging if possible
  3. Roll out with monitoring
  4. Prepare rollback plan
  5. Document changes made

Read the full file on GitHub · 160 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. 2d ago First seen · 160 lines · 44 tokens per session scan A 25bdba5ccd1b

Subscribe to this mod's changes

gideon is an agent published in the GitHub repository CarbeneAI/Forge (9 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 1,126 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.