Borrowing it
Nothing to install: this file belongs to Jott2121/agent-gate. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Jott2121/agent-gate/main/.cursor/skills/verify-receipts/SKILL.mdgit clone --depth 1 https://github.com/Jott2121/agent-gateWrote 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/skills/jott2121/agent-gate/verify-receipts)<a href="https://agentmods.dev/skills/jott2121/agent-gate/verify-receipts"><img src="https://agentmods.dev/badge/skills/jott2121/agent-gate/verify-receipts/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.
<a href="https://agentmods.dev/skills/jott2121/agent-gate/verify-receipts"><img src="https://agentmods.dev/badge/skills/jott2121/agent-gate/verify-receipts.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00048 | $0.00499 |
| Opus 5.5 | $0.00019 | $0.00200 |
| Sonnet 5.5 | $0.00010 | $0.00100 |
| Haiku 4.5 | $0.00005 | $0.00050 |
Grade A, and why
verify-receipts 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 4d 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
Verify receipts
- Read AGENTS.md "Commands". From the repo root, run:
pip install -e ".[dev]" pytest-cov- Tests, including the coverage gate (do not lower 90):
python -m pytest -q --cov=agent_gate --cov-report=term-missing --cov-fail-under=90 - Receipts:
python scripts/check_receipts.py - Lint and typecheck: n/a. There is no ruff or mypy config, no
eval/harness, and no--checkscorer. Capture exit codes and the last ~20 lines of each.
git diff origin/main -- README.md docs/ WRITEUP.md— list every number that changed. For each, find the command that produces it and re-run it. If you can't reproduce it, mark it UNVERIFIED and stop; do not open the PR as ready. Known gap: README says "currently 97% covered".scripts/check_receipts.pyprints the percentage from the pytest command above. If they differ, report both. Leave the sentence alone unless the PR's purpose is to update that published number. The16.7%sentence cites sabot. Do not recompute it in this repo. Demo hash prefixes in the README are not stable receipts. Ledger hashes include a timestamp.- Run
python3 scripts/scan_blocked_terms.py(employer terms, whole tree, no exempt files) and grep the diff for secret patterns (see.cursor/rules/40-security-and-data.mdc). Any hit, or a scanner exit code other than 0, means stop and report. - Confirm
--cov-fail-under=90is unchanged and no tests were skipped, xfailed, or removed. - Output a Markdown block:
- Commands run + pass/fail
- Numbers: before → after → command → reproduced? (Y/N)
- Not verified / known gaps
- Paste that block into the PR's "How verified" section. Never claim a check passed that you didn't run.
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.
- 4d ago First seen · 24 lines · 48 tokens per session scan A 7362909c8a2e
verify-receipts is a skill published in the GitHub repository Jott2121/agent-gate (3 stars, last pushed yesterday), licensed MIT. It adds 48 tokens to every session and 499 once invoked, about $0.0002 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 2026-10-12.
Other skills, from other repositories
pytest-suite
Write or extend the backend test suite following this project's conventions. Use when adding tests for a new service/route/repository, when coverage is missing, or when asked to test a feature. Knows the mocked-session + httpx AsyncClient setup so tests run with no database.
pydantic-ai-testing
Test PydanticAI agents using TestModel, FunctionModel, VCR cassettes, and inline snapshots. Use when writing unit tests, mocking LLM responses, or recording API interactions.
Unit Test Scaffold (Python/pytest)
Generate Python/pytest unit test skeletons from specifications.
mcp-tool-developer
Build Model Context Protocol (MCP) servers and tools from scratch. Full-stack MCP development with TypeScript/Python, testing, deployment, and registry publishing.
implement
Implement an agreed specification through existing seams with tests, checks, and review.
rust-testing
Rust testing patterns including unit tests, integration tests, async testing, property-based testing, mocking, and coverage. Follows TDD methodology.