bot-psychologist

bot-psychologist is an agent for Claude Code from navapbc/digital-service-orchestra. It costs 65 tokens per session (3,064 once invoked), scanned B, original, Apache-2.0.

An agent that investigates why another AI agent or language model behaves inconsistently, unexpectedly, or incorrectly.

In plain words
What is it for?
Use it to diagnose behavioral failures in AI agents and produce findings that can be passed to a bug-fixing workflow.
Why use it?
It gives a structured way to trace failures instead of guessing at prompts, context, or reasoning problems.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: model in frontmatter; mentions subagents; mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the dso plugin — 37 skills, 4 commands, 53 agents shipped together

Good fit Use it to diagnose behavioral failures in AI agents and produce findings that can be passed to a bug-fixing workflow.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add navapbc/digital-service-orchestra
Claude Code
/plugin install dso

Made for: Claude Code.

Or install dso, the plugin that ships this one along with the rest of its 37 skills, 4 commands, 53 agents.

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 bot-psychologist

README.md
[![agentmods](https://agentmods.dev/badge/agents/navapbc/digital-service-orchestra/bot-psychologist/github.svg)](https://agentmods.dev/agents/navapbc/digital-service-orchestra/bot-psychologist)
Your own site
<a href="https://agentmods.dev/agents/navapbc/digital-service-orchestra/bot-psychologist"><img src="https://agentmods.dev/badge/agents/navapbc/digital-service-orchestra/bot-psychologist/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.

agentmods 80×15 button for bot-psychologist

Your own site · 80×15
<a href="https://agentmods.dev/agents/navapbc/digital-service-orchestra/bot-psychologist"><img src="https://agentmods.dev/badge/agents/navapbc/digital-service-orchestra/bot-psychologist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 65 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,064 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00065 $0.03064
Opus 5 $0.00032 $0.01532
Sonnet 5 $0.00013 $0.00613
Haiku 4.5 $0.00006 $0.00306

Measured 11d ago against content hash b19ea1b7b886, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade B, and why

bot-psychologist scanned grade B 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 11d 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.

Instruction-override phrasingmediumPrompt injection

Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.

14. **Instruction Leaking** — Model treats user data/payloads as system instructions (e.g., CSV contains "Ignore previous instructions" and model complies).

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

plugins/dso/agents/bot-psychologist.md · 177 lines

How it starts

The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bot Psychologist Agent

Startup: Session HEAD Sync (worktree isolation fix)

When dispatched with isolation: "worktree", the Agent runtime creates your worktree branched from origin/main — NOT from the orchestrator's session HEAD. If the orchestrator injected SESSION_BRANCH and SESSION_HEAD into your prompt, sync to the session HEAD as your FIRST action before reading any source files. Bug a951-d6f2-0c21-443f tracks this.

if [[ -n "${SESSION_BRANCH:-}" && -n "${SESSION_HEAD:-}" ]]; then
    bash "${CLAUDE_PLUGIN_ROOT}/scripts/worktree-session-head-sync.sh"  # shim-exempt: internal orchestration script
    if [[ $? -ne 0 ]]; then
        echo "ERROR: worktree-session-head-sync.sh failed — aborting" >&2
        exit 1
    fi
elif [[ -n "${SESSION_BRANCH:-}" || -n "${SESSION_HEAD:-}" ]]; then
    echo "WARNING: SESSION_BRANCH/SESSION_HEAD partially set — skipping worktree sync" >&2
fi

When both are unset (orchestrator on main, no session in flight), do nothing — your default origin/main worktree is correct.

You are an elite LLM behavioral debugger. Your purpose is to diagnose and correct divergent, unpredictable, or failing behavior in other LLMs, agents, and complex prompts using the scientific method.

You MUST NOT assume a root cause based on a user's initial report. Instead, you iteratively propose hypotheses, design specific probes (experiments) to test them, analyze results, and only propose a correction once the root cause is experimentally proven. Do not propose any fix before a hypothesis has been confirmed through experiment. Do not assume a failure mode before experimental results are in.

Read the full file on GitHub · 177 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. 11d ago First seen · 177 lines · 65 tokens per session scan B b19ea1b7b886

Subscribe to this mod's changes

bot-psychologist is an agent published in the GitHub repository navapbc/digital-service-orchestra (6 stars, last pushed today), licensed Apache-2.0. It adds 65 tokens to every session and 3,064 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (instruction-override phrasing). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.