agentmods.dev

diagnose

diagnose is a skill for Claude Code from productstein/holomime. It costs 75 tokens per session (492 once invoked), scanned A, original, MIT.

A command-line checker for finding behavior problems in AI-agent conversations, such as repeated apologies, excessive uncertainty, agreement with false claims, or made-up information.

In plain words
What is it for?
Use it to inspect conversation logs and report detected patterns with their severity, frequency, and example excerpts.
Why use it?
It helps reveal recurring response patterns that may make an agent unreliable or inconsistent, using rule-based checks rather than another language-model review.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the holomime plugin — 6 skills shipped together

not rated 1repo 7mo ago A scan 75 tokens original MIT

Good fit Use it to inspect conversation logs and report detected patterns with their severity, frequency, and example excerpts.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/productstein/holomime/diagnose
View source ↗ productstein/holomime holomime.com
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.

Any agent
npx skills add productstein/holomime --skill diagnose
Clone the repo
git clone --depth 1 https://github.com/productstein/holomime

Made for: Claude Code.

Or install holomime, the plugin that ships this one along with the rest of its 6 skills.

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 diagnose

README.md
[![agentmods](https://agentmods.dev/badge/skills/productstein/holomime/diagnose/github.svg)](https://agentmods.dev/skills/productstein/holomime/diagnose)
Your own site
<a href="https://agentmods.dev/skills/productstein/holomime/diagnose"><img src="https://agentmods.dev/badge/skills/productstein/holomime/diagnose/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 diagnose

Your own site · 80×15
<a href="https://agentmods.dev/skills/productstein/holomime/diagnose"><img src="https://agentmods.dev/badge/skills/productstein/holomime/diagnose.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 492 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00075 $0.00492
Opus 5.5 $0.00030 $0.00197
Sonnet 5.5 $0.00015 $0.00098
Haiku 4.5 $0.00007 $0.00049

Measured 2mo ago against content hash 4295682c5a64, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

diagnose 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 2mo 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.

integrations/claude-code-skill/skills/diagnose/SKILL.md · 49 lines

What it actually says

Behavioral Diagnosis

Run holomime's 8 rule-based detectors against conversation logs to identify behavioral drift patterns.

Usage

npx holomime diagnose $ARGUMENTS

If no path is provided, look for conversation logs in the current directory. Common locations:

  • .holomime/logs/ — holomime alignment session logs
  • Exported chat transcripts (Claude, ChatGPT, JSONL)

What It Detects

Detector What It Catches
Apology Excessive "sorry", "apologize", "pardon"
Hedging "maybe", "perhaps", "possibly" stacking (3+ per response)
Sycophancy Excessive agreement, especially with contradictions
Boundary Should-refuse situations, boundary violations
Error Spiral Repeated errors without recovery
Sentiment Skewed positive/negative ratio
Formality Register inconsistency (formal ↔ informal oscillation)
Retrieval Fabrication, hallucination, overconfidence markers

For full detector reference, see detectors.md.

Output

Each pattern found includes:

  • Severity: concern (high) or warning (moderate)
  • Prevalence: percentage of responses affected
  • Examples: actual excerpts from the conversation

Gotchas

  • If you get "no logs found", specify the path explicitly: npx holomime diagnose ./path/to/logs
  • Supported formats: claude (Claude export), openai (ChatGPT export), jsonl (generic), otel (OpenTelemetry)
  • This is rule-based (regex + word patterns) — zero LLM API calls, runs in < 5 seconds
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. 2mo ago First seen · 49 lines · 75 tokens per session scan A 4295682c5a64

Subscribe to this mod's changes

diagnose is a skill published in the GitHub repository productstein/holomime (1 stars, last pushed 7mo ago), licensed MIT. It adds 75 tokens to every session and 492 once invoked, about $0.0003 per session on Opus 5.5. 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.

AI SafetyBuilding agentsDebuggingai-agentsbehavioral-intelligencebehavioral-therapybig-five-psychologydpo-training
Related

diagnose compared with skills from other repositories

diagnose next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
diagnoseproductstein/holomimeSkill17mo agoMITA75Claude Code
learning-from-experienceFlyFission/nuclear-grade-context-engineeringSkill332d agoMITA65Claude Code
reporting-shared-defectsFlyFission/nuclear-grade-context-engineeringSkill332d agoMITA93Claude Code
responding-to-incidentsFlyFission/nuclear-grade-context-engineeringSkill332d agoMITA80Claude Code
thumbgate-doctorIgorGanapolsky/ThumbGateSkill30todayMITA168Claude Code
prevention-rulesIgorGanapolsky/ThumbGateSkill30todayMITA18Cursor
shellcheck-configurationaisa-group/skill-injectSkill1014d agoMITB35Claude Code, Codex