Borrowing it
Nothing to install: this file belongs to DilawarShafiq/unworldly. 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/DilawarShafiq/unworldly/master/.claude/commands/sp.phr.mdgit clone --depth 1 https://github.com/DilawarShafiq/unworldlyWrote 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/dilawarshafiq/unworldly/sp.phr)<a href="https://agentmods.dev/commands/dilawarshafiq/unworldly/sp.phr"><img src="https://agentmods.dev/badge/commands/dilawarshafiq/unworldly/sp.phr.svg" alt="Measured on agentmods" 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 | $0.00019 | $0.01842 |
| Opus 5 | $0.00010 | $0.00921 |
| Sonnet 5 | $0.00004 | $0.00368 |
| Haiku 4.5 | $0.00002 | $0.00184 |
Grade A, and why
sp.phr 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.
This is a copy
100% identical to sp.phr — 390 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
COMMAND: Record this AI exchange as a structured PHR artifact
CONTEXT
The user has just completed work (or is requesting work) and needs to capture this exchange as a Prompt History Record (PHR) for:
- Learning and pattern recognition (spaced repetition)
- Team knowledge sharing and traceability
- Compliance and audit requirements
- Building a searchable corpus of effective prompts
User's input to record:
$ARGUMENTS
CRITICAL: The complete text above is the PROMPT to preserve verbatim. Do NOT truncate to first line only.
YOUR ROLE
Act as a meticulous documentation specialist with expertise in:
- Knowledge management and organizational learning
- Software development lifecycle documentation
- Metadata extraction and classification
- Creating structured, searchable technical records
QUICK OVERVIEW (strict)
After completing ANY work, automatically create a PHR:
- Detect work type: constitution|spec|plan|tasks|implementation|debugging|refactoring|discussion|general
- Generate title: 3-7 word descriptive title summarizing the work
- Capture context: COMPLETE conversation (never truncate to summaries)
- Route correctly:
- Pre-feature work →
history/prompts/ - Feature-specific work →
specs/<feature>/prompts/
- Pre-feature work →
- Confirm: Show "📝 PHR-NNNN recorded"
OUTPUT STRUCTURE (with quick flywheel hooks)
Execute this workflow in 5 sequential steps, reporting progress after each:
Step 1: Execute User's Request (if not already done)
If the user provided a task/question in $ARGUMENTS:
- Complete the requested work first
- Provide full response to user
- Then proceed to Step 2 to record the exchange
If you already completed work and user just wants to record it:
- Skip to Step 2
Step 2: Determine Stage and Routing
Select ONE stage that best describes the work:
Constitution (→ history/prompts/constitution/):
constitution- Defining quality standards, project principles
Feature-specific (→ history/prompts/<feature-name>/ - requires feature context):
spec- Creating feature specificationsplan- Architecture design and technical approachtasks- Implementation breakdown with test casesred- Debugging, fixing errors, test failuresgreen- Implementation, new features, passing testsrefactor- Code cleanup, optimizationexplainer- Code explanations, documentationmisc- Other feature-specific work
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 First seen · 196 lines · 19 tokens per session scan A fbdf18a194a6
sp.phr is a command published in the GitHub repository DilawarShafiq/unworldly (9 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 1,842 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to sp.phr, differing in 390 lines, and is treated as a copy.
Other commands, from other repositories
graduate
Graduate a Lovable / Bolt / v0 export to GitHub Actions + a non-platform deploy target via the Starter Series 5-step path. Orchestrates the three audit MCP tools and surfaces lift-in steps for the matching starter.
seed-security-guidance
Generate a starter claude-security-guidance.md at the repo root tailored to the detected Starter Series template. Anthropic's Claude Code Security Guidance Plugin (released 2026-05-26) reads this file as an in-session guard.
audit-security
Check baseline CI security hygiene against the Starter Series bar — gitleaks, CodeQL, dep audit, license check, --ignore-scripts, Dependabot grouped, secret-scanning, claude-code-security-review, claude-security-guidance. Read-only, complementary to Anthropic's in-session security guidance plugin.
proof-report
Generate a Launch Proof Report for an existing repo by combining release, publish, and security audit evidence.
audit-cd
Check publish drift across destination registries — npm, PyPI, Open VSX, VS Marketplace, AMO (Firefox), GitHub Releases — via public read APIs. Read-only, makes outbound HTTPS.
audit-release
Diagnose release-readiness against the Starter Series quality bar — matched starter, version-vs-last-tag drift, CHANGELOG drift vs merged PRs, and publish-workflow kind. Read-only.