Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

JSONExport

ASecurity

Export the reconciled Claude Code session receipt as JSON — the machine-readable artifact to keep, diff, or feed to another tool. Use when the user asks for the data, the JSON, an export, a receipt file, or something to download or process programmatically.

2 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentsbashgit

Works with

claude codemcp

Security Analysis

A100/100

Scanned 9/19/2026

$npx -y skills add jagmeetchawla/gitreceipts --skill JSONExport --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of JSONExport?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for JSONExport
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/jagmeetchawla-jsonexport/badge)](https://www.skillsdirectory.com/skills/jagmeetchawla-jsonexport)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
description: Export the reconciled Claude Code session receipt as JSON — the machine-readable artifact to keep, diff, or feed to another tool. Use when the user asks for the data, the JSON, an export, a receipt file, or something to download or process programmatically.
---

# JSON export — the receipt as data

`git receipts export` runs the same pipeline as the audit and emits the
reconciled result as JSON: per-commit statement, claim ledger, residue,
commands with their failure classes, MCP calls, intents, token estimates,
provenance, exceptions, blast radii, identity roll-up. **Every number
matches the console and the HTML** — three renderings of one receipt.

This is the artifact to hand over: commit it beside the code, diff two runs
against each other, feed it to another program, or give it to a model to
interpret. It is far smaller than the raw session log it distills.

## Run it

Requires the `git-receipts` binary (0.1.1+) — `/gitreceipts:recap` owns the
install and upgrade offers if it's missing or old.

```bash
F="${TMPDIR:-/tmp}/gitreceipts-receipt.json"
git receipts export > "$F" && echo "$F"
```

**Write it to a file and give the path — never paste the JSON into the
conversation.** A real receipt is megabytes; it belongs in a file the user
downloads or opens, not in context.

Scopes are the same as everywhere: `--commit <hash>`, `--project` (a
`{project, repos: […]}` wrapper), `--latest`, `--this-session <marker>`,
`--full-history`. Shape flags: `--compact` (single line, for piping),
`--full` (the whole transcript plus every command's output — the maximal
export).

## What to tell them

- The schema is versioned (`schema_version`) and **additive-only within
  0.x** — new fields may appear, existing ones never change meaning. The
  full promise is in `docs/COMPAT.md` in the repo.
- If they're building on it: read defensively, ignore unknown fields, and
  treat optional fields as optional (`resolution`, `diagnosis`,
  `landed_at`, `failure_class` are omitted rather than null).

## Privacy — read this before sharing one

The export is the most complete artifact of the three, and unlike a report
nobody skims it before passing it on. It carries prompts, command text, and
captured output verbatim. Whenever the user mentions sharing, committing,
or uploading it, name the flags in the same breath: `--no-intent` (drops
prompts and agent prose; every count stays), `--no-identity` (drops names
and emails), `--redact <word>`. Home paths are masked automatically.
**Never pass `--no-scan`** — the secret/PII scanner stays on, always.

Attribution

jagmeetchawlajagmeetchawla
View sourceSee grades on GitHubMore from jagmeetchawla →
SSkills Directory ProSkills Directory

Get any skill into Claude in one click.

Download any skill as a ZIP for Claude.ai, Claude Desktop, or .claude/skills. $9/mo.

See Pro

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills Directory ProSkills Directory

Get any skill into Claude in one click.

Download any skill as a ZIP for Claude.ai, Claude Desktop, or .claude/skills. $9/mo.

See Pro

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1087401 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

697551 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →