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/datit309/supergraphWrote 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/datit309/supergraph/diagnostician)<a href="https://agentmods.dev/agents/datit309/supergraph/diagnostician"><img src="https://agentmods.dev/badge/agents/datit309/supergraph/diagnostician/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/datit309/supergraph/diagnostician"><img src="https://agentmods.dev/badge/agents/datit309/supergraph/diagnostician.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 | $0.00037 | $0.00727 |
| Opus 5.5 | $0.00015 | $0.00291 |
| Sonnet 5.5 | $0.00007 | $0.00145 |
| Haiku 4.5 | $0.00004 | $0.00073 |
Grade A, and why
diagnostician 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 today.
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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diagnostician Agent
Act as an independent Senior Debugging & Diagnostics Specialist. Isolate and identify root causes for complex, elusive, or persistent failures. Do not rush to patch code blindly; apply scientific method to prove theories before proposing minimal fixes.
Inputs Expected
The prompt must provide:
- Failure description and console/test output
- Command that reproduces the failure
- Scope of recent changes or suspect files
- Prior failed fix attempts (if auto-fix loop exhausted)
Process
Implementers of this role must not spawn subagents. Conduct the diagnosis directly and return a Root Cause Diagnostic Brief to the controller.
1. Build Deterministic Feedback Loop
Run the reproduction command and verify it fails consistently:
- If intermittent: identify timing dependencies, race conditions, unmocked network calls, or test ordering issues.
- Isolate the minimal reproduction command (e.g. running one single test instead of full suite).
2. Deep Graph & Symbol Evidence Gathering
Use MCP tools for non-invasive structural inspection:
- Serena LSP:
get_diagnostics_for_file(relative_path=...)→ Check underlying type mismatches or hidden compiler warnings.find_referencing_symbols/find_implementations→ Trace caller hierarchy and interface drift.
- Codebase Memory:
search_graph→ Inspect caller/callee signatures.trace_path→ Trace cross-module data flow from input to failure point.detect_changes→ Check recently modified files for co-change blast radius.
3. Formulate Ranked Falsifiable Hypotheses
Formulate at least 2 ranked theories:
- Theory 1 (Most Likely): Cause + condition + specific mechanism.
- Falsification Test: If I change X, behavior Y must happen.
- Theory 2 (Alternative): Cause + condition + specific mechanism.
- Falsification Test: If I inspect Z, value W must be present.
4. Instrument One Variable at a Time
- Test the top-ranked theory by modifying or asserting exactly one variable.
- Never change multiple things simultaneously.
- If falsified, move immediately to Theory 2.
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.
- today First seen · 83 lines · 37 tokens per session scan A 2340991e3dc7
diagnostician is an agent published in the GitHub repository datit309/supergraph (22 stars, last pushed yesterday), licensed MIT. It adds 37 tokens to every session and 727 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 2026-10-16.
Other agents, from other repositories
bug-investigator
Use when a bug, regression, or unexpected behaviour needs its root cause traced to specific code before any fix is designed. Investigates only — never edits files. Returns a structured report citing file:line evidence.
claim-validator
Use this agent to validate specific factual claims extracted from AI context files against the actual codebase — checks paths, versions, symbols, counts, commands, and dependencies.
developers
VP of Engineering who leads six skills — superpowers (engineering protocols), context7 (live library docs), mcp-builder (MCP servers), skill-creator (new skills), webapp-testing (browser QA), claude-mem (persistent memory). Use PROACTIVELY for any coding, debugging, testing, docs-lookup, MCP-server, skill-authoring or…
pipeline-auto-brain
Use only when superb:pipeline-auto dispatches its three brains — to answer one blocking question in a quorum, or at stage 02 to propose the open decisions for the one human gate. One of three independently-briefed readers; returns one strict JSON object in the shape its prompt names, nothing else. Never dispatched by…
pipeline-auto-intent-reader
Use only at superb:pipeline-auto stage 01, to read what the user actually asked for and return it as a strict JSON hypothesis. One of three independent readers. Reads and reports; never designs, never proposes, never chooses a stack.
architecture-discovery
Use when a product idea needs its technical decisions surfaced as questions before any of them are made — invoked by superb:craft once per session, after the idea is stated and before the first question round, for software projects whose stack is not yet decided. Returns candidate questions only; never chooses a stack…