A file-timestamping tool that records a file’s SHA-256 fingerprint on Polygon, a blockchain network, through ProofLedger. It saves a proof bundle beside the file.

Use it to timestamp documents, build artifacts, releases, or other files and obtain proof and verification links.

It provides dated evidence that the exact file existed by a certain time without sending the file itself. Only the fingerprint and, unless hidden, the file name are sent.

anchor — Skill for Claude Code by Fulcrum-Enterprises/verify-proof

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add Fulcrum-Enterprises/verify-proof --skill anchor

Clone the repo

git clone --depth 1 https://github.com/Fulcrum-Enterprises/verify-proof

Made for: Claude Code.

Or install proofledger, the plugin that ships this one along with the rest of its 2 skills, 1 MCP server.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/fulcrum-enterprises/verify-proof/anchor/github.svg)](https://agentmods.dev/skills/fulcrum-enterprises/verify-proof/anchor)

Your own site

<a href="https://agentmods.dev/skills/fulcrum-enterprises/verify-proof/anchor"><img src="https://agentmods.dev/badge/skills/fulcrum-enterprises/verify-proof/anchor/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/fulcrum-enterprises/verify-proof/anchor"><img src="https://agentmods.dev/badge/skills/fulcrum-enterprises/verify-proof/anchor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 538 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.

Model	Per session	Once invoked
Fable 5.1	$0.00065	$0.00538
Opus 5.5	$0.00026	$0.00215
Sonnet 5.5	$0.00013	$0.00108
Haiku 4.5	$0.00006	$0.00054

Measured today against content hash 96e7ec3b968b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

anchor 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 today.

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-plugin/skills/anchor/SKILL.md · 23 lines

What it actually says

Anchor a file with ProofLedger

Use the verify-proof MCP tools. The file is hashed on this machine; only its SHA-256 hash is sent to ProofLedger, plus the file name unless the user asks to keep it private.

Steps

Confirm which file or files to anchor. Each proof counts toward the user's monthly API allowance (the free plan includes 100 a month), so anchor what was asked for, not whole folders by default.
One file: call create_proof with the path. Pass send_filename: false if the user does not want the name sent. Several files (up to 100): call create_proofs_batch; file names double as the proofs' own ids, so re-running on unchanged files returns their existing proofs. If a file changed but kept its name, the batch returns its old proof, which will not match the new file: anchor that file with create_proof instead, or rename it.
If the tool answers that there is no API key, show the user the steps it returns (a free key, no card) and stop there. The key belongs in the PROOFLEDGER_API_KEY environment variable of the shell that starts Claude Code; a new session picks it up. Never ask the user to paste the key into the chat.
Report the proof id, the certificate link and the verification link from the tool's answer.
The Polygon anchor usually lands within a minute. Check with get_proof_status. Once it reads anchored, call save_proof_bundle with the proof id and an output_path next to the file, named <file name>.proof.json. With the bundle saved, anyone can check the file later without ProofLedger, using the verify skill or verify-proof verify <file> --proof <bundle>.

What to tell the user

A proof shows that a file with this exact SHA-256 fingerprint existed by the anchor time, and that the file has not changed since.
It does not show who made the file, and it is not a copyright registration.
Do not describe the file as "verified by ProofLedger". The proof is a dated record on a public chain, not an endorsement.

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.

today Changed 96e7ec3b968b
2d ago First seen · 23 lines · 65 tokens per session scan A e13fda4c79dc

Subscribe to this mod's changes

anchor is a skill published in the GitHub repository Fulcrum-Enterprises/verify-proof (0 stars, last pushed yesterday), licensed MIT. It adds 65 tokens to every session and 538 once invoked, about $0.0003 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 2026-10-17.

Web3 and blockchain blockchain cli cryptography merkle-tree polygon proof-of-existence

blockchain-cryptography

Use this skill when asked about cryptographic primitives in blockchain, elliptic curve cryptography, hash functions, Merkle trees, digital signatures, zero-knowledge proofs, key derivation, BIP standards, and blockchain-specific crypto implementations. Languages: C++, Rust, Go, Python. Covers secp256k1, BN254…

j4flmao/agent-skills · 201 tokens

blockchain-core

Use this skill when asked about blockchain fundamentals, consensus mechanisms, PoW, PoS, gas, staking, blockchain data structures, DAG consensus, Avalanche, MEV, PBS, economic security, blockchain node implementation. Languages: C++, Go. Covers core protocol engineering including consensus algorithms (Nakamoto, PBFT…

j4flmao/agent-skills · 175 tokens

stablecoin-chain-explorer

Explore stablecoin TVL distribution and yield opportunities by blockchain. Query which chains have the most stablecoins, compare cross-chain yields, and find the best opportunities on Ethereum, BSC, Arbitrum, Base, Polygon, and more. Also for protocols and issuers researching where stablecoin TVL and liquidity…

barkermoney/barker-mcp · 102 tokens

anchor