Borrowing it
Nothing to install: this file belongs to tensorbee/rdocx. 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/tensorbee/rdocx/main/.claude/commands/microscope.mdgit clone --depth 1 https://github.com/tensorbee/rdocxWrote 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/tensorbee/rdocx/microscope)<a href="https://agentmods.dev/commands/tensorbee/rdocx/microscope"><img src="https://agentmods.dev/badge/commands/tensorbee/rdocx/microscope/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/tensorbee/rdocx/microscope"><img src="https://agentmods.dev/badge/commands/tensorbee/rdocx/microscope.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 | $0.00017 | $0.01602 |
| Opus 5.5 | $0.00007 | $0.00641 |
| Sonnet 5.5 | $0.00003 | $0.00320 |
| Haiku 4.5 | $0.00002 | $0.00160 |
Grade A, and why
microscope 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 6d 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/microscope F-XXX [--working] [--aspect NAME]
Review the implementation diff for one F-ID. This command changes no code.
It is required before /complete-feature and it is not skippable.
--working reviews the uncommitted working tree, which is the normal mode.
Without it, review the F-ID's commits on the sprint branch.
Steps
-
Establish the diff.
git difffor--working, otherwise the F-ID's commit range against the sprint base. State the file and line count so the scope is on the record. -
Read the contract first.
.claude/plans/F-XXX-design.md, then the citeddocs/hld/sections. A review that does not know the intent can only find typos. -
Review by aspect. Default aspects, or one named by
--aspect:Aspect Looks for correctnessWrong logic, off-by-one, unhandled cases, wrong operator precedence contractDoes it do what the design plan said, and nothing more panicsunwrap,expect, indexing, slicing, arithmetic overflow on untrusted inputooxmlSchema child order, namespace prefixes, whitespace preservation, unmodelled subtrees dropped rather than captured testsDoes the test gate actually prove the story. Would it fail if the code were reverted structureThe rules in AGENTS.md. New traits, generics, wrappers without a second implementer today -
Challenge the acceptance evidence. For every changed semantic rule, trace the consumer map through actual callers. Look for duplicated policy hidden behind a shared parser/formatter. Check a risk-based combination the existing tests might collapse: multilevel context, zero items with implicit lookup, fresh versus held handles, or final completion metadata. Name which plausible wrong behavior the fixture rejects. Rendering claims need actual positioned/render output. Native parity needs actual native evidence. Recorded tests may be consumed without rerunning them, but inspect their assertions and inputs rather than accepting aggregate pass counts.
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.
- 6d ago Changed · +56 lines 2e131f65f14a
- 26d ago First seen · 92 lines · 17 tokens per session scan A 6d8697963a75
microscope is a command published in the GitHub repository tensorbee/rdocx (44 stars, last pushed yesterday), licensed MIT. It adds 17 tokens to every session and 1,602 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 2026-10-04.
Other commands, from other repositories
refactor-clean
Refactor provided code for cleanliness, maintainability, and alignment with SOLID principles and modern best practices — no over-engineering.
deep-audit.skeleton
Description: This section is populated by Bootstrap with manifest data. Required manifest fields: project.description, stack.primary, project.structure, project.subprojects, stack.orm, stack.authmethod Example output.
harness:audit
Cross-dimensional codebase audit orchestrator — classify repo shape, fan out parallel read-only audit agents, dedup and severity-rank findings against existing issues, publish grouped tracking issues.
modify
Command "modify" from MartyBonacci/specswarm, covering user input, flag parsing, parse flags from arguments, mode routing and goal.
prism-graph
Export Prism's graph of this repository and summarise it.
hotfix
Ship a fast branch-based P0 hotfix — diagnose, implement, open a ready-for-review PR, then verify + review after (deferred by design).