Who it is forA reviewer or auditor who receives a sealed report folder and must confirm it has not been altered.
The problemA reader has to trust the report on faith unless they can recompute its hashes and re-check its claims independently.
The outcomeA JSON or SARIF result showing whether the seal hash and each claim re-check still hold.
What you need first
- DeepSeek Harness (dsh) installed, as described in the Compatibility section of the README
- npm available to install the plugin
- A workspace where the harness can write the default .research-ledger and research-reports directories
- Source text or workspace files to register as evidence
Steps
- Install the plugin with
dsh plugin --profile demo add dsh-research-reportso the verifier is available. - Locate the sealed report directory, which contains report.md, manifest.json, verification.jsonl, and disconfirmation.jsonl.
- Run
dsh-research-verify --report <report-dir> --format jsonto get a JSON envelope with the recomputed results. (inferred, check the README) - Run
dsh-research-verify --report <report-dir> --format sarifif your tooling reads SARIF 2.1.0. (inferred, check the README) - Compare the recomputed seal hash with the seal hash printed when the report was sealed.
Prompt for your agent
Use the dsh-research-verify CLI from the dsh-research-report repo on the sealed report at <report-dir>. Expected output: a JSON envelope or SARIF document that reports the recomputed seal hash and per-claim results. Verify that the recomputed seal hash matches the one recorded in manifest.json before reporting the report as intact.
Caveat. The verifier recomputes hashes and re-runs byte checks from the sealed directory, so it cannot judge whether the sources themselves were right.
Get 5 new use cases every morning. Free, one short email, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Disclaimer
Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page