Borrowing it
Nothing to install: this file belongs to pantoum-spfx/pantoum. 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/pantoum-spfx/pantoum/main/.claude/commands/pantoum-analyze.mdgit clone --depth 1 https://github.com/pantoum-spfx/pantoumWrote 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/pantoum-spfx/pantoum/pantoum-analyze)<a href="https://agentmods.dev/commands/pantoum-spfx/pantoum/pantoum-analyze"><img src="https://agentmods.dev/badge/commands/pantoum-spfx/pantoum/pantoum-analyze/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/pantoum-spfx/pantoum/pantoum-analyze"><img src="https://agentmods.dev/badge/commands/pantoum-spfx/pantoum/pantoum-analyze.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 | $0.01442 |
| Opus 5 | $0.00000 | $0.00721 |
| Sonnet 5 | $0.00000 | $0.00288 |
| Haiku 4.5 | $0.00000 | $0.00144 |
Grade A, and why
pantoum-analyze 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 11d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PANTOUM Upgrade Analyzer
Perform a defensive post-mortem analysis of PANTOUM upgrade results. This is the most important plugin command — it diagnoses what happened during an upgrade by reading the report files.
Analysis Principles
- Be critical, not paranoid — analyze with a critical eye, but be fair. PANTOUM has safeguards (verification builds, patch validation, AI retry loops). When those safeguards worked and the outcome is GREEN, report it with confidence. Reserve alarming language for actual problems.
- Never modify the solution — this skill is read-only analysis. Do not attempt to fix, patch, edit, or update any files in the solution. Only read and report.
- Present evidence — always cite specific files, error messages, and metrics. Don't speculate without data.
- Proportionate severity — label severity based on what actually happened, not what could theoretically go wrong. A PnP migration that passed all verification checks is "info", not "high severity". A failed patch with no workaround is "critical".
- Include a testing reminder — always recommend testing in SharePoint before deploying, but keep it brief and matter-of-fact for GREEN outcomes. Don't frame routine testing as a crisis.
Output Formatting
- Never expose internal phase numbers in your output. Use descriptive headings like "Quick Health Summary", "Detailed Analysis", "Diagnosis", etc. — not "Phase 1", "Phase 3".
- Interactive vs static mode — when invoked from the webapp (indicated by a "non-interactive session" note in the context), end the report after the Recommendations section. Do not include follow-up menus or "What would you like to do next?" prompts. When invoked interactively in Claude Code, present the Phase 5 follow-up menu as normal.
Phase 1: Locate
Ask the user for the solution path (or use the current directory).
Search for pantoum_run_* directories using Glob:
pantoum_run_*/pantoum_final-report_*.json
Handle these cases:
- None found — inform the user that no upgrade reports were found. Suggest running
/pantoum-upgradefirst. - Multiple found — list all found directories with their timestamps and let the user select which to analyze.
- Single found — auto-proceed with that directory.
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.
- 11d ago First seen · 135 lines · 0 tokens per session scan A 9958751dc7c2
pantoum-analyze is a command published in the GitHub repository pantoum-spfx/pantoum (5 stars, last pushed 13d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,442 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
bootstrap
Verifies and repairs the Claude Code Toolkit installation.
build-fix
A build-error fixing procedure for TypeScript projects. It runs the project build, groups and explains errors, applies fixes one at a time, and checks the build again.
fix-issue
Analyze and fix the GitHub issue: $ARGUMENTS.
gates-csk
Gate report — what the tool-level gates actually did, and which rules nothing has tripped.
perf-profile.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
refactor-cleanup.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.