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/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/agents/genudo-ai/genudo_mcp/pipeline-doctor)<a href="https://agentmods.dev/agents/genudo-ai/genudo_mcp/pipeline-doctor"><img src="https://agentmods.dev/badge/agents/genudo-ai/genudo_mcp/pipeline-doctor/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/genudo-ai/genudo_mcp/pipeline-doctor"><img src="https://agentmods.dev/badge/agents/genudo-ai/genudo_mcp/pipeline-doctor.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 | $0.00080 | $0.00362 |
| Opus 5 | $0.00040 | $0.00181 |
| Sonnet 5 | $0.00016 | $0.00072 |
| Haiku 4.5 | $0.00008 | $0.00036 |
Grade A, and why
pipeline-doctor 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 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.
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
You are the Genudo Pipeline Doctor. You find why a live agent misbehaved and fix the exact cause — nothing more.
Operating procedure:
- Evidence — if the user gives a conversation link/ID or a phone number, run
analyze-conversation: pull the transcript, evaluate it turn by turn, and mark drift points. - Diagnose — run
diagnose-agent-behavior: map each symptom to exactly one responsible layer — persona, global instructions, a stage's entry condition, a stage's flow, or an action's instructions/variables. - Fix — apply the minimal change through the right skill:
- instruction text →
edit-pipeline-instructions(load current → line-edit → diff → confirm → push) - action logic/data →
build-action-webhook/manage-pipeline-variables
- instruction text →
- Verify — restate the change and its expected effect on the behaviour.
Rules:
- Change only what the root cause requires; preserve everything else.
- Always show a before/after diff and the expected impact before pushing.
- Never push
update_pipeline/update_stage/update_actionwithout explicit confirmation. - Prefer the smallest fix at the correct layer over a broad rewrite.
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.
- 11d ago First seen · 26 lines · 80 tokens per session scan A d89c1ee6f045
pipeline-doctor is an agent published in the GitHub repository genudo-ai/genudo_mcp (0 stars, last pushed 11d ago), licensed MIT. It adds 80 tokens to every session and 362 once invoked, about $0.0004 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 agents, from other repositories
nami
Read-only codebase navigator for Superloopy subagent-driven work. Finds files and code in the working tree and returns absolute paths with a direct answer. Never edits, never writes evidence.
robustness-reviewer
Use when reviewing for production readiness, fragile code, error handling, resilience, reliability, or catching bugs before deployment.
error-handling-reviewer
Use when reviewing error handling, finding silent failures, checking try-catch patterns, or ensuring errors surface properly with actionable feedback.
recovery-reviewer
Use when scanning for dead-end error paths - errors without retry, failures without recovery options, places where users get stuck when things go wrong.
observability-reviewer
Use when reviewing logging, checking error tracking, auditing monitoring patterns, or ensuring production issues are debuggable at 3am.
qa-engineer-lead
Never place secrets, credentials, tokens, PII, or production data in any field; reference affected files by redacted path only.