What is patch-receipt?

A workflow for producing replayable proof that a software change works, using images, videos, HTTP checks, or web and mobile app checks.

Verifying UI fixes, visual regressions, interactions, backend requests, and Android or iOS app behavior.

It reduces uncertainty about whether a fix really changed the intended behavior and gives reviewers evidence they can inspect.

patch-receipt — Skill for Codex by vivekparekh8

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 vivekparekh8/patch-receipt --skill patch-receipt

Clone the repo

git clone --depth 1 https://github.com/vivekparekh8/patch-receipt

Made for: Codex.

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/vivekparekh8/patch-receipt/patch-receipt/github.svg)](https://agentmods.dev/skills/vivekparekh8/patch-receipt/patch-receipt)

Your own site

<a href="https://agentmods.dev/skills/vivekparekh8/patch-receipt/patch-receipt"><img src="https://agentmods.dev/badge/skills/vivekparekh8/patch-receipt/patch-receipt/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/vivekparekh8/patch-receipt/patch-receipt"><img src="https://agentmods.dev/badge/skills/vivekparekh8/patch-receipt/patch-receipt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,015 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	$0.00098	$0.01015
Opus 5.5	$0.00039	$0.00406
Sonnet 5.5	$0.00020	$0.00203
Haiku 4.5	$0.00010	$0.00102

Measured 2mo ago against content hash e9f658c15cf9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

patch-receipt 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 2mo 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.

skills/patch-receipt/SKILL.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PatchReceipt

Create proof another reviewer can inspect and replay. Verify the behavior with the strongest existing project test, preserve source evidence, normalize the comparison, annotate the subject, verify hashes, and publish only after explicit confirmation.

Workflow

Define one falsifiable claim before editing. State the separate expected before and after outcomes.
Capture the real before state before the fix. If lost, recover it from the base revision or a separate worktree and disclose reconstruction.
Match viewport/device, route/screen, seed data, interaction, locale, orientation, authentication/app state, and timing.
Choose the evidence path:
- Existing PNG/JPEG/MP4: use media.
- Executable request/response semantics: use http.
- Web, Android, or iOS work: read references/verification.md, run the targeted native/project verification, and capture its checkpoints as PNG or MP4 for a media recipe.
Read references/recipe-format.md before writing the final recipe. Do not move the recipe afterward; the receipt binds its path and hash.
Run patchreceipt doctor. Resolve missing required CLI tools before continuing. Do not auto-install or configure optional MCP, browser, emulator, simulator, SDK, or device tooling.
Generate evidence:
- Media or captured UI: patchreceipt build <recipe.json>
- Backend/API: patchreceipt capture-http <recipe.json>
- Backend/API secrets: provide only referenced PATCHRECEIPT_SECRET_* names and explicitly list them with --allow-env.
Run patchreceipt verify <output-directory>. Treat behavioral assertions, CLI receipt integrity, and API assertion success as separate results.
Inspect PNGs at full size, representative video frames, the complete MP4 interaction, saved assertions, and redacted supplementary evidence. Confirm boxes surround only the claimed subject.
Review all evidence for credentials, personal data, device ids, signed-in browser state, internal hosts, signing data, or unrelated content.
Summarize the claim, behavioral result, recipe, receipt, and limitations. Read references/publishing.md only when publication is requested.

Read the full file on GitHub · 48 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

2mo ago First seen · 48 lines · 98 tokens per session scan A e9f658c15cf9

Subscribe to this mod's changes

patch-receipt is a skill published in the GitHub repository vivekparekh8/patch-receipt (7 stars, last pushed 2mo ago), licensed MIT. It adds 98 tokens to every session and 1,015 once invoked, about $0.0004 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 2026-08-31.

Testing

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

cua-driver

Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.

davidondrej/skills · 68 tokens

patch-receipt