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.
npx skills add genudo-ai/genudo_mcp --skill diagnose-agent-behaviorgit clone --depth 1 https://github.com/genudo-ai/genudo_mcpWrote 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/genudo-ai/genudo_mcp/diagnose-agent-behavior)<a href="https://agentmods.dev/skills/genudo-ai/genudo_mcp/diagnose-agent-behavior"><img src="https://agentmods.dev/badge/skills/genudo-ai/genudo_mcp/diagnose-agent-behavior/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/genudo-ai/genudo_mcp/diagnose-agent-behavior"><img src="https://agentmods.dev/badge/skills/genudo-ai/genudo_mcp/diagnose-agent-behavior.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 | $0.00107 | $0.00427 |
| Opus 5 | $0.00053 | $0.00214 |
| Sonnet 5 | $0.00021 | $0.00085 |
| Haiku 4.5 | $0.00011 | $0.00043 |
Grade A, and why
diagnose-agent-behavior 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 10d 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.
What it actually says
Diagnose Agent Behavior
Find the root cause of a behavioural problem and point to the one place that fixes it.
Steps
- Clarify the symptom — what did the agent do, in which situation, and what was expected?
If there's a real conversation, use
analyze-conversationfirst for evidence. - Load the agent —
list_pipelines(persona + global instructions) andlist_pipeline_stages(each stage'senter_condition+instructions). If an action is involved,list_variablesand review the action'sinstructions. - Localize — map the symptom to exactly one responsible layer:
- wrong identity/tone → persona
- a rule that should hold everywhere but doesn't → global instructions
- entered/skipped a stage at the wrong time → that stage's enter_condition
- wrong steps or order inside a stage → that stage's instructions
- action fired at the wrong moment or with wrong data → the action (instructions/variables)
- Propose the fix — name the field, quote the offending text, and give the corrected intent.
Output
Write diagnosis.md: symptom → evidence → responsible field → proposed change → which skill
applies it (edit-pipeline-instructions, build-action-webhook, or manage-pipeline-variables).
This skill does not write to the account; hand off through the edit skills' confirmation gates.
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.
- 10d ago First seen · 30 lines · 107 tokens per session scan A b1d940c74bfa
diagnose-agent-behavior is a skill published in the GitHub repository genudo-ai/genudo_mcp (0 stars, last pushed 11d ago), licensed MIT. It adds 107 tokens to every session and 427 once invoked, about $0.0005 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.
Other skills, from other repositories
superloopy-doctor
Use when diagnosing Superloopy doctor, install, wrapper, plugin cache, hook bootstrap, bundled agents, marketplace, Codex, Claude Code, stale-version, evidence-floor, or host-wiring health problems.
cordis-plugin-sofagent-rollback
A sofagent plugin for undoing changes in reverse order after an error, using Git snapshots and cleanup handlers for registered effects.
cloudflare-observability-mcp
Observability MCP server by Cloudflare.
OpenClaw 网络优化助手
A Chinese-language guide for diagnosing and safely improving a computer’s network, including DNS, proxies, VPNs, and routing. DNS translates website names into network addresses; a proxy or VPN routes traffic through another service.
n8n-validation-expert
Interpret validation errors and guide fixing them. Use when encountering validation errors, validation warnings, false positives, operator structure issues, or need help understanding validation results. Also use when asking about validation profiles, error types, the validation loop process, or auto-fix capabilities.…
exposed-service-triage
Triages exposed TCP listeners found by security audits. Use for: exposed port, what is listening, fix exposed service, open port.