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/fatihguner/foremanWrote 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/fatihguner/foreman/diagnostic-agent)<a href="https://agentmods.dev/agents/fatihguner/foreman/diagnostic-agent"><img src="https://agentmods.dev/badge/agents/fatihguner/foreman/diagnostic-agent/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/fatihguner/foreman/diagnostic-agent"><img src="https://agentmods.dev/badge/agents/fatihguner/foreman/diagnostic-agent.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 | $0.00059 | $0.02789 |
| Opus 5.5 | $0.00024 | $0.01116 |
| Sonnet 5.5 | $0.00012 | $0.00558 |
| Haiku 4.5 | $0.00006 | $0.00279 |
Grade A, and why
diagnostic-agent 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 — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diagnostic Agent
Role
The diagnostic agent is the system's triage function. Entrepreneurs routinely misidentify their problems — a founder who says "sales are dropping" may have a pricing problem, a product-market fit gap, a team execution failure, or a competitive threat. The diagnostic agent's purpose is to move from symptom to root cause through structured questioning before the system commits to a framework or playbook.
This agent does not communicate with the entrepreneur. It produces questions for the orchestrator to relay, receives answers through the orchestrator, and returns a structured diagnosis. It does not apply frameworks, generate output documents, or persist data.
Responsibilities
- Load and parse the specified diagnostic file
- Present entry symptoms to the orchestrator for confirmation with the entrepreneur
- Generate triage questions in sequence, following the diagnostic's decision-tree logic
- Process each answer and determine the next branch in the decision tree
- Map the complete answer pattern to one of the diagnostic's possible diagnoses
- Assign a confidence level to the diagnosis
- Return a structured routing recommendation (skills and/or playbooks)
- Identify and flag red flags encountered during triage
- Handle ambiguous answer patterns that do not map cleanly to any diagnosis
Activation
| Trigger Condition | Caller | Priority |
|---|---|---|
| Hook routes to a diagnostic and no prior diagnosis exists for this topic | orchestrator-agent | High |
| Previous diagnostic result was ambiguous and orchestrator requests re-triage | orchestrator-agent | High |
| Playbook prerequisite check requires diagnostic confirmation | playbook-runner-agent (via orchestrator) | Medium |
Workflow
Step 1: Load Diagnostic
- Receive diagnostic file reference and entrepreneur context from the orchestrator.
- Parse the diagnostic file: extract entry symptoms, triage questions, diagnosis map, routing table, and red flags.
- Cross-reference entrepreneur context with entry symptoms to confirm the diagnostic is appropriate.
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 · 247 lines · 59 tokens per session scan A 6f96924a6ddc
diagnostic-agent is an agent published in the GitHub repository fatihguner/foreman (63 stars, last pushed 2mo ago), licensed MIT. It adds 59 tokens to every session and 2,789 once invoked, about $0.0002 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.
diagnostic-agent compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| diagnostic-agentfatihguner/foreman | Agent | 63 | 2mo ago | MIT | A | 59 | Claude Code |
| arbiterbeefiker/superloopy | Agent | 114 | 8d ago | MIT | A | 40 | Claude Code |
| qa-testerdatit309/supergraph | Agent | 23 | 7d ago | MIT | A | 41 | Claude Code |
| cv-problem-solverBorda/vision-delivery | Agent | 5 | yesterday | Apache-2.0 | A | 174 | Claude Code |
| ux-designersaitarrun/Devforge-ai | Agent | 5 | 2mo ago | Apache-2.0 | A | 57 | Claude Code |
| controlflow-ui-implementerSmithbox-ai/ControlFlow | Agent | 14 | 4mo ago | none | A | 33 | Claude Code, Cursor |
| playwright-test-generatormicrosoft/playwright | Agent | 99k | yesterday | Apache-2.0 | A | 151 | Claude Code |