agentleFS
ProvableHQProvableHQ/snarkVM/.claude/CLAUDE.md

snarkVM

CLAUDE.md1.2k starsChanged 21 days agoApache-2.0View on GitHub

@../AGENTS.md Use .claude/workspace/ for scratch files (gitignored). For PRs with 30+ files or 1000+ lines: fetch metadata + file list only, triage by risk (consensus > circuit > crypto), deep-dive selectively, write findings to workspace after each file, synthesize at end. Always paginate: review threads (100+), comments (10+), commits (30+), PR comments (30+). Use --paginate for REST, loop on hasNextPage for GraphQL.

Trending

More talk lately.about the whole repository

Dec 2025: 2 mentionsJan 2026: 2 mentionsFeb 2026: 1 mentionMar 2026: 1 mentionApr 2026: 1 mentionMay 2026: 3 mentionsJun 2026: 4 mentionsJul 2026: 3 mentionsAug 2026: 7 mentionsSep 2026: 7 mentionsOct 2026: 8 mentionsNov 2026: 0 mentions
Dec 2025Jun 2026Nov 2026
Mentions a month of the ProvableHQ/snarkVM repository that our weekly crawl found. There is no adoption data for this file yet.

Who's talking about ProvableHQ/snarkVM

The biggest 5 of 50 mentions linking to the repository that our crawl found. Each line is their own headline.

See all 50

Talked about on GitHub (50 times).

On GitHub · 50

45 more on GitHub

The file

We split this CLAUDE.md into the rules it gives an agent

4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use .claude/workspace/ for scratch files (gitignored).

    line 5
  2. Very specific:

    Always paginate: review threads (100+), comments (10+), commits (30+), PR comments (30+).

    line 28
  3. Very specific:

    Use --paginate for REST, loop on hasNextPage for GraphQL.

    line 29
  4. Distinctive:

    Read state files for progress — continue from last completed step.

    line 34

≈ “Common” is an estimate: at least 1 in 5 of the 27,641 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
CLAUDE.md

@../AGENTS.md

Workspace

Use .claude/workspace/ for scratch files (gitignored).

.claude/workspace/
├── context-{type}-{id}.json    # Structured data (PR metadata, files list)
├── state-{type}-{id}.md        # Human-readable state + progress log
└── handoff-{type}-{id}.md      # Cross-skill communication

Memory Rules

  • Summarize, don't retain — extract findings to scratch files, discard raw data.
  • Fetch incrementally — file list first, then per-file diffs as needed.
  • Rotate context — write findings before switching to a new area.
  • Re-read scratch files — use workspace state instead of scrolling back.
  • Index what you've done — track progress in structured scratch files.

Large PR Protocol

For PRs with 30+ files or 1000+ lines: fetch metadata + file list only, triage by risk (consensus > circuit > crypto), deep-dive selectively, write findings to workspace after each file, synthesize at end.

Pagination

Always paginate: review threads (100+), comments (10+), commits (30+), PR comments (30+). Use --paginate for REST, loop on hasNextPage for GraphQL.

Session Recovery

  1. Check workspace: ls .claude/workspace/
  2. Read state files for progress — continue from last completed step.
  3. Re-fetch if context is stale.
<claude-mem-context></claude-mem-context>

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.