Borrowing it
Nothing to install: this file belongs to sandeep-alluru/agentdelta. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sandeep-alluru/agentdelta/main/.claude/commands/inspect.mdgit clone --depth 1 https://github.com/sandeep-alluru/agentdeltaWrote 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/commands/sandeep-alluru/agentdelta/inspect)<a href="https://agentmods.dev/commands/sandeep-alluru/agentdelta/inspect"><img src="https://agentmods.dev/badge/commands/sandeep-alluru/agentdelta/inspect/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/commands/sandeep-alluru/agentdelta/inspect"><img src="https://agentmods.dev/badge/commands/sandeep-alluru/agentdelta/inspect.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 | $0.00000 | $0.00227 |
| Opus 5.5 | $0.00000 | $0.00091 |
| Sonnet 5.5 | $0.00000 | $0.00045 |
| Haiku 4.5 | $0.00000 | $0.00023 |
Grade A, and why
inspect 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 1mo 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
Inspect an agentdelta trace file and summarize the agent's execution path.
Usage: /project:inspect <trace.jsonl>
Steps:
- Run:
agentdelta inspect $ARGUMENTS - Present a clean summary:
- Total steps and run_id
- Sequence of node types (start → llm → tool_call → tool_return → ... → end)
- Each tool call: name and truncated arguments
- Each LLM step: first 100 chars of reasoning
- Any metadata fields present
- Highlight anything unusual:
- More than 10 steps (complex agent run)
- Repeated tool calls (possible loop)
- Missing start or end node
- Very short LLM reasoning (< 20 chars — may be truncated or empty)
Context:
- Trace format: each line is JSON with "type": "node"|"edge"|"trace_meta"
- Node types: start, llm, tool_call, tool_return, end
- Node IDs are content-addressed (SHA-256[:16]) — same content = same ID across runs
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.
- 1mo ago First seen · 23 lines · 0 tokens per session scan A 56fa091b3cef
inspect is a command published in the GitHub repository sandeep-alluru/agentdelta (0 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 227 tokens. 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 commands, from other repositories
fire-resurrect
Autonomous Resurrection Mode — reverse-engineer intent from messy code, then rebuild clean from scratch.
fire-debug
Systematic debugging with persistent state, skills library integration, and WARRIOR validation.
fire-reflect
After any failure (debug resolution, test failure, approach rotation, stalled loop), capture what was tried, why it failed, and what actually worked as a persistent reflection. Future sessions search these before investigating.
fire-verify-uat
Conversational User Acceptance Testing with automatic parallel diagnosis on failures.
refactor
Code-level refactoring analysis and roadmap generation.
celigo-troubleshoot
Diagnose a failing, partial, empty, or stuck Celigo flow -- read its runs, errors, and execution logs, find the root cause, and say what to fix. Read-only until I ask for the fix.