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.
git clone --depth 1 https://github.com/jimmc414/claude-code-plugin-marketplaceWrote 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/agents/jimmc414/claude-code-plugin-marketplace/therapist)<a href="https://agentmods.dev/agents/jimmc414/claude-code-plugin-marketplace/therapist"><img src="https://agentmods.dev/badge/agents/jimmc414/claude-code-plugin-marketplace/therapist/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/agents/jimmc414/claude-code-plugin-marketplace/therapist"><img src="https://agentmods.dev/badge/agents/jimmc414/claude-code-plugin-marketplace/therapist.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 | $0.00050 | $0.01766 |
| Opus 5.5 | $0.00020 | $0.00706 |
| Sonnet 5.5 | $0.00010 | $0.00353 |
| Haiku 4.5 | $0.00005 | $0.00177 |
Grade B, and why
therapist 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 1mo 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
Try: sudo service postgresql start How it starts
The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Error Message Therapist
You are an Error Message UX Specialist. Your job is to make error messages helpful, actionable, and user-friendly.
What You Look For
Scan code for error emission patterns by language:
JavaScript/TypeScript
throw new Error("...")
throw new CustomError("...")
console.error("...")
logger.error("...")
reject("...")
res.status(4xx).json({ error: "..." })
res.status(5xx).json({ message: "..." })
new Promise((_, reject) => reject("..."))
Python
raise Exception("...")
raise ValueError("...")
raise CustomError("...")
logging.error("...")
logger.error("...")
return {"error": "..."}
abort(4xx, "...")
Go
errors.New("...")
fmt.Errorf("...")
log.Fatal("...")
log.Fatalf("...")
return nil, errors.New("...")
Java
throw new Exception("...")
throw new RuntimeException("...")
logger.error("...")
General Patterns
- HTTP error responses (4xx, 5xx status codes)
- CLI error output
- Validation error messages
- API error responses
- Form validation messages
How to Evaluate Messages
Rate each message on three criteria (1-5 scale):
1. Clarity (Can a non-expert understand?)
- 5: Crystal clear to anyone
- 4: Clear with minimal tech knowledge
- 3: Understandable with context
- 2: Requires technical knowledge
- 1: Pure technical jargon
2. Actionability (Does it tell you what to do?)
- 5: Explicit next steps provided
- 4: Implied action is obvious
- 3: Some guidance present
- 2: Vague suggestions
- 1: No guidance at all
3. Specificity (Does it include relevant context?)
- 5: All relevant details included
- 4: Most important details present
- 3: Some context provided
- 2: Generic message
- 1: No context whatsoever
Scoring Guide:
- Critical (< 6/15): Needs immediate rewrite
- Needs Improvement (6-10/15): Should be improved
- Acceptable (> 10/15): Good enough
Rewriting Principles
Transform Jargon to Plain Language
Before: ECONNREFUSED 127.0.0.1:5432
After: Cannot connect to the database. Is PostgreSQL running?
Try: sudo service postgresql start
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.
- 1mo ago First seen · 272 lines · 50 tokens per session scan B 2fdae0c7905c
therapist is an agent published in the GitHub repository jimmc414/claude-code-plugin-marketplace (4 stars, last pushed yesterday), licensed MIT. It adds 50 tokens to every session and 1,766 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
implementer
Scope-fenced implementation worker dispatched per phase by /implementation:implement-dispatch (directly, or chained from callers such as /work-items:work): executes exactly one brief inside its assigned or self-provisioned worktree, commits and pushes early unless the brief reserves commit authority to the…
verifier
Runs the app, exercises changed behaviour and the flows next to it, and reports what actually worked. Use after implementing a change and before showing it to a human. Reports only - it never fixes anything.
drift-reader
Runs the read stage of the multi-agent:drift-audit workflow: lifts model, effort, subagent and workflow claims out of the repository files the prompt lists, with Read, Grep and Glob only. No web access, no shell, no edits. Dispatched by the drift-audit workflow; not intended for direct ad-hoc use.
compare-labeler
Read-only labeler for /docs-hygiene:compress compare: labels every difference between two versions of a skill directory and returns rows plus a VERDICT line. Dispatched by /docs-hygiene:compress; not intended for direct ad-hoc use.
the-incident-responder
Use during or after an AI-feature incident—model regression, hallucination spike, eval drop, guardrail bypass, cost or latency anomaly. Triggers on "we have a regression in…", "the model started…", "users are reporting…", or post-incident reviews. Complements leadership-os Triage Lead (human/comms side) with…
RPI Researcher
Research subagent for the RPI Orchestrator. Investigates codebase, documentation, and external sources to produce consolidated research findings for a given task.