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.
git clone --depth 1 https://github.com/David405/harness-kitWrote 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/rules/david405/harness-kit/verify-claims-with-evidence)<a href="https://agentmods.dev/rules/david405/harness-kit/verify-claims-with-evidence"><img src="https://agentmods.dev/badge/rules/david405/harness-kit/verify-claims-with-evidence.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 | $0.00307 | $0.00307 |
| Opus 5 | $0.00153 | $0.00153 |
| Sonnet 5 | $0.00061 | $0.00061 |
| Haiku 4.5 | $0.00031 | $0.00031 |
Grade A, and why
verify-claims-with-evidence 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 7d 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.
What it actually says
No unverified claims
Every factual claim about code, schemas, contracts, configuration or history is checked against the source before it is stated, and the evidence is shown. Applies to chat, review comments, findings, contracts, and commit messages.
Before stating it
- Read the artifact — the file, the migration, the test, the command output. Not memory, not inference from a filename, not "typically this works like".
- Cite it — path plus symbol, or the command and its output, so a reader can re-run the check.
- Distinguish did from should. "The handler persists amounts" requires having read the handler. "It should persist amounts" is a proposal and must be worded as one.
When it cannot be verified
Say so, and name what would settle it. Never round an assumption up to a fact.
Re-check your own prior statements
Before a claim goes on the record, re-check it against the code as committed, not as you remember writing it. Claims that were true of a draft go stale.
Aggregate claims — "all of", "every", "nothing else changed" — need a command whose output covers the whole set, not a spot check.
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.
- 7d ago First seen · 32 lines · 307 tokens per session scan A 2f0c4cee5e7b
verify-claims-with-evidence is a cursor rule published in the GitHub repository David405/harness-kit (2 stars, last pushed 9d ago), licensed Apache-2.0. It adds 307 tokens to every session, about $0.0015 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 2026-08-31.
Other cursor rules, from other repositories
clean-code-reviewer
Eliminates technical debt using SOLID, DRY, YAGNI, and Addy Osmani production-grade engineering principles. / TR: SOLID, DRY, YAGNI ve Addy Osmani üretim seviyesi mühendislik ilkeleri ile kod kalitesini denetleyen yetenek.
sweep-benchmarks
Audit xrspatial modules for asv benchmark coverage gaps: missing benchmarks, backend parameterization gaps, unrepresentative inputs, broken or silently-skipped benchmarks.
code-review
BMAD BMM Agent: code-review.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.