alethfeld: Command for Claude Code

.claude/commands/fix-sorries.md

fix-sorries is a command for Claude Code from tobiasosborne/alethfeld. It costs 10 tokens per session (519 once invoked), scanned A, original, MIT.

A workflow for finding and replacing sorry statements in Lean 4 code. In Lean, sorry marks a proof as temporarily unfinished.

In plain words
What is it for?
Use it to locate sorries, study their theorem context, choose proof tactics or existing lemmas, and build the Lean project after each fix.
Why use it?
It organizes unfinished proofs by dependency and checks each proposed replacement with the Lean build, reducing the chance of leaving incomplete formal verification behind.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the TodoWrite tool.

This is tobiasosborne/alethfeld's own configuration. It tells Claude Code how to work on alethfeld itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything alethfeld configures →

Reuse

Borrowing it

Nothing to install: this file belongs to tobiasosborne/alethfeld. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/tobiasosborne/alethfeld/legacy/.claude/commands/fix-sorries.md
Clone the repo
git clone --depth 1 https://github.com/tobiasosborne/alethfeld

Made for: Claude Code.

Wrote 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.

agentmods badge for fix-sorries

README.md
[![agentmods](https://agentmods.dev/badge/commands/tobiasosborne/alethfeld/fix-sorries/github.svg)](https://agentmods.dev/commands/tobiasosborne/alethfeld/fix-sorries)
Your own site
<a href="https://agentmods.dev/commands/tobiasosborne/alethfeld/fix-sorries"><img src="https://agentmods.dev/badge/commands/tobiasosborne/alethfeld/fix-sorries/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.

agentmods 80×15 button for fix-sorries

Your own site · 80×15
<a href="https://agentmods.dev/commands/tobiasosborne/alethfeld/fix-sorries"><img src="https://agentmods.dev/badge/commands/tobiasosborne/alethfeld/fix-sorries.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 519 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00010 $0.00519
Opus 5 $0.00005 $0.00260
Sonnet 5 $0.00002 $0.00104
Haiku 4.5 $0.00001 $0.00052

Measured 11d ago against content hash 2ac1b233ed89, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

fix-sorries 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.

.claude/commands/fix-sorries.md · 80 lines

What it actually says

Sorry Elimination Protocol

Systematically find and fix all sorry statements in the Lean 4 codebase.

Phase 1: Discovery

  1. Run lake build to get current state:

    cd lean && lake build 2>&1
    
  2. Find all sorries:

    grep -rn "sorry" --include="*.lean" lean/AlethfeldLean/
    
  3. Create a todo list with all sorry locations, ordered by dependency (fix dependencies first).

Phase 2: Analysis

For each sorry:

  1. Read the context - the theorem statement, available lemmas, imports
  2. Understand what needs to be proved - the goal type
  3. Check Mathlib for relevant lemmas that could help
  4. Identify the proof strategy:
    • Direct computation?
    • Apply existing lemma?
    • Induction?
    • Case split?
    • Rewrite chain?

Phase 3: Fix

For each sorry (in dependency order):

  1. Attempt the fix using appropriate tactics:

    • simp, ring, linarith for arithmetic
    • exact, apply, refine for applying lemmas
    • rw for rewrites
    • constructor, use for existentials
    • intro, intros for implications/universals
  2. Build and check:

    cd lean && lake build 2>&1 | head -50
    
  3. If successful: Mark todo complete, move to next

  4. If stuck: Note the issue, create a beads issue, move on

Phase 4: Verification

After all sorries addressed:

  1. Full build:

    cd lean && lake build
    
  2. Count remaining sorries:

    grep -c "sorry" lean/AlethfeldLean/**/*.lean 2>/dev/null || echo "0"
    
  3. Report results

Output

Track progress with TodoWrite. Report:

  • Total sorries found
  • Sorries fixed
  • Sorries remaining (with reasons)
  • Build status
Changes

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.

  1. 11d ago First seen · 80 lines · 10 tokens per session scan A 2ac1b233ed89

Subscribe to this mod's changes

fix-sorries is a command published in the GitHub repository tobiasosborne/alethfeld (144 stars, last pushed 3mo ago), licensed MIT. It adds 10 tokens to every session and 519 once invoked, about $0.0001 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.