Borrowing it
Nothing to install: this file belongs to safety-quotient-lab/psychology-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/safety-quotient-lab/psychology-agent/main/.claude/skills/diagnose/SKILL.mdgit clone --depth 1 https://github.com/safety-quotient-lab/psychology-agentWrote 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/skills/safety-quotient-lab/psychology-agent/diagnose)<a href="https://agentmods.dev/skills/safety-quotient-lab/psychology-agent/diagnose"><img src="https://agentmods.dev/badge/skills/safety-quotient-lab/psychology-agent/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.
<a href="https://agentmods.dev/skills/safety-quotient-lab/psychology-agent/diagnose"><img src="https://agentmods.dev/badge/skills/safety-quotient-lab/psychology-agent/diagnose.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 | $0.00019 | $0.04178 |
| Opus 5.5 | $0.00008 | $0.01671 |
| Sonnet 5.5 | $0.00004 | $0.00836 |
| Haiku 4.5 | $0.00002 | $0.00418 |
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.
How it starts
The opening of the file, as written. The whole thing — 503 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/diagnose — Systemic Self-Diagnostic
Five-level diagnostic hierarchy for the psychology agent cogarch. Higher numbers run faster with less depth; lower numbers run slower with more thoroughness. Level 1 replaces manual QA.
Design reference: five-tier diagnostic depth model adapted from the structured diagnostic protocol in Sternbach & Okuda (1991), Star Trek: The Next Generation Technical Manual. Level 1 requires the most resources and produces the most complete picture; Level 5 produces a status snapshot with minimal overhead. The key design insight from that reference: lower diagnostic numbers indicate higher thoroughness, not lower priority — a convention this system adopts.
Diagnostic Levels
| Level | Scope | Depth | Systems Affected | Estimated Duration |
|---|---|---|---|---|
| 5 | Status poll | Row counts, binary health indicators | None — read-only | ~10 seconds |
| 4 | Targeted subsystem | Detail queries for one subsystem | None — read-only | ~30 seconds |
| 3 | Standard sweep | All subsystems, key metrics, findings | None — read-only | ~2 minutes |
| 2 | Cross-system analysis | L3 + drift detection, alignment checks, pattern analysis | None — read-only | ~5 minutes |
| 1 | Full integrity verification | L2 + file checks, governance verification, hook validation, CLI tests, orphan detection | Writes test records (cleaned up) | ~10 minutes |
Default: Level 3.
Usage:
/diagnose — Level 3, all subsystems
/diagnose 5 — Level 5, status poll
/diagnose 4 claims — Level 4, claims subsystem deep scan
/diagnose 1 — Level 1, full integrity verification (replaces manual QA)
Recommended cadence:
| Level | When |
|---|---|
| 5 | Session start — quick pulse before work begins |
| 4 | When a specific subsystem shows degraded status |
| 3 | Every 5-10 sessions; after /cycle as health check |
| 2 | After schema migrations, bootstrap rebuilds, infrastructure changes |
| 1 | After major refactors; before release tags; after long idle periods |
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.
- 2mo ago First seen · 503 lines · 19 tokens per session scan A 3aaf51962452
diagnose is a skill published in the GitHub repository safety-quotient-lab/psychology-agent (23 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 19 tokens to every session and 4,178 once invoked, about $0.0001 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 2026-08-30.
diagnose compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| diagnosesafety-quotient-lab/psychology-agent | Skill | 23 | 6mo ago | Apache-2.0 | A | 19 | Claude Code |
| systematic-debuggingopen-metadata/OpenMetadata | Skill | 16k | yesterday | Apache-2.0 | A | 37 | Claude Code |
| log-error-digestzebbern/claude-code-guide | Skill | 4.7k | 3d ago | MIT | A | 71 | Claude Code, Codex |
| cwv-optimizeradobe/skills | Skill | 319 | yesterday | Apache-2.0 | A | 112 | Claude Code |
| ci-fixersipyourdrink-ltd/bernstein | Skill | 1.2k | yesterday | Apache-2.0 | A | 15 | Claude Code, Codex |
| triaging-web-analytics-supportPostHog/posthog | Skill | 41k | yesterday | none | A | 151 | Claude Code, Codex |
| diagnosing-missing-recordingsPostHog/posthog | Skill | 41k | yesterday | none | A | 76 | Claude Code, Codex |