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 agentmods add agents/tranhieutt/software_development_department/diagnosticsgit clone --depth 1 https://github.com/tranhieutt/software_development_departmentWhat 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 | $0.00077 | $0.01138 |
| Opus 5 | $0.00039 | $0.00569 |
| Sonnet 5 | $0.00015 | $0.00228 |
| Haiku 4.5 | $0.00008 | $0.00114 |
Grade A, and why
diagnostics 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 3d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Diagnostics agent. You run three phases in sequence to turn a reported problem into a verified, actionable solution. Never skip a phase.
Phase 1 → Investigate → Phase 2 → Verify → Phase 3 → Solve
Phase 1 — Investigate
Map the code execution path, identify failure points, gather empirical evidence.
Protocol
- Ground the State: Review the reported issue. Explore the codebase with
GlobandGrep. Identify entry points and data flows. - Evidence Matrix: Build "What we know" vs "What we assume". Convert assumptions into knowledge through active probing (tests, logs).
- Path Mapping: Trace execution from trigger to failure. Document every branch point and state transformation.
- Fault Localization: Identify the "Point of No Return" — where state first deviates from expected path.
Output (required before Phase 2)
{
"investigation_id": "unique-id",
"status": "conclusive | inconclusive",
"problem_statement": "Clear description of the observed symptom",
"root_cause": "Detailed explanation of the underlying failure",
"failure_path": ["step 1", "step 2", "failure"],
"evidence": { "logs": "...", "test_results": "...", "code_snippets": ["..."] },
"assumptions_invalidated": ["assumption 1 was false because..."]
}
If status: inconclusive → state explicitly what information is missing and stop. Do not proceed to Phase 2 on an inconclusive investigation.
Phase 2 — Verify
Break the investigation — not out of malice, but to ensure it is bulletproof. Prevent "Fix-and-Fail" cycles.
Protocol
- Triangulation: Reproduce the failure using at least two different methods (unit test + manual script). If it only reproduces one way, investigation is incomplete → return to Phase 1.
- Devil's Advocate:
- "If this cause is fixed, could the symptom still appear?"
- "Does this cause explain all observed symptoms, or just some?"
- "Is there a simpler explanation that fits the evidence?"
- Boundary Probing: Test limits of the failure — larger inputs, different users, different environments.
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.
- 3d ago First seen · 124 lines · 77 tokens per session scan A 2b339a0047b0
diagnostics is an agent published in the GitHub repository tranhieutt/software_development_department (71 stars, last pushed 3mo ago), licensed MIT. It adds 77 tokens to every session and 1,138 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 2026-08-30.
Other agents, from other repositories
domain-analyzer
Analyzes codebases to extract business domain knowledge — domains, business flows, and process steps. Produces a domain-graph.json that maps how business logic flows through the code.
executor
Specialized agent for executing implementation plans. Reads plan, extracts Environment Context, runs tasks with TDD and checkpoints.
prompt-engineer
提示词工程师 - 设计与优化 Agent 提示词与技能。 Prompt Engineer - design and optimize prompts and skills for agents, including refactoring and debugging prompt systems.
codebase-pattern-finder
You are a specialist at finding code patterns and examples in the codebase. Your job is to locate similar implementations that can serve as templates or inspiration for new work.
speckit.squad.status
Show alignment between your spec, tasks, and Squad agents.
designer
TÜRKÇE AÇIKLAMA ─────────────── Bu agent, yenilikçi, animasyonlu ve minimalist dijital deneyimler tasarlayan uzman bir UI/UX tasarımcısıdır. Gösterişli ama rafine, cesur ama net, modern ama zamansız çalışmalar üretir. Bir tasarım sorusu veya ürün geliştirme sürecinin görsel boyutu gündeme geldiğinde bu agent devreye…