Receipts Control
- 1 installs
- Updated February 3, 2026
- 24601/receipts
receipts-control is a Claude Code skill for operating the Receipts observability stack: starting the OpenTelemetry collector, tailing and backfilling AI-agent logs, checking status, and querying stored telemetry.
About
receipts-control is a Claude Code skill that operates the Receipts observability stack on a developer machine. It starts and stops the OpenTelemetry collector, tails and backfills AI-agent session logs, checks status, and queries locally stored JSONL telemetry. Receipts captures agent tool usage, prompts, and outputs as OTLP logs across Claude Code, Codex, Gemini CLI, and OpenCode. A developer uses it to audit and query what local AI agents did, across tools and machines.
- Operates the Receipts observability stack: start/stop the OpenTelemetry collector, tail logs, and check status
- Backfills Codex session history and queries locally stored JSONL telemetry with ripgrep
- Guards changes: always asks before editing ~/.claude/settings.json, exporting to remote Loki, or changing redaction
Receipts Control by the numbers
- 1 all-time installs (skills.sh)
- Ranked #1,173 of 1,435 DevOps & CI/CD skills by installs in the Skillselion catalog
- Data as of Jul 28, 2026 (Skillselion catalog sync)
receipts-control capabilities & compatibility
Free and local; runs an OpenTelemetry collector on the developer machine. No API keys required for local operation.
- Capabilities
- agent observability · log tailing · telemetry backfill · log query · collector management
- Works with
- grafana
- Use cases
- devops · debugging · data analysis
- Pricing
- Free
What receipts-control says it does
Use this skill to operate the Receipts observability stack on a developer machine.
Control, view, query, and maintain Receipts observability (start/stop collector, tail logs, backfill history, check status, and update the repo).
npx skills add https://github.com/24601/receipts --skill receipts-controlAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 1 |
|---|---|
| Last updated | February 3, 2026 |
| Repository | 24601/receipts ↗ |
What it does
A developer starts the Receipts OpenTelemetry collector, backfills agent history, and queries logs to audit what local AI agents did.
Who is it for?
Developers who want to audit and query local AI-agent tool usage and telemetry through an OpenTelemetry collector
Skip if: Users who need a hosted/SaaS observability product or who are not running local AI agents
When should I use this skill?
The user asks to operate Receipts, start or check the collector, backfill history, or inspect/query agent logs
What you get
The Receipts collector runs and agent telemetry is captured, backfilled, and queryable as OTLP/JSONL logs.
- running OTLP collector writing JSONL logs
- backfilled Codex session telemetry
- queryable agent-interaction logs
By the numbers
- supports 4 agents (Claude Code, Codex, Gemini CLI, OpenCode)
- 3 asks-before-acting guardrails
Files
Receipts Control
Use this skill to operate the Receipts observability stack on a developer machine.
Fast status checks
- Check collector running:
pgrep -f "otelcol-contrib" || true- Check recent logs:
ls -la otel-logsStart the Collector (no daemon required)
./scripts/receipts-collector.sh configs/otel-collector.yamlFor Loki export:
./scripts/receipts-collector.sh configs/otel-collector.loki.yamlTail Codex sessions
agent-otel tail-codexBackfill history
agent-otel backfill-codexQuery locally stored JSONL
rg '"gen_ai.tool.name"' otel-logs/interactions.jsonlUpdate Receipts
Use the update script:
./scripts/receipts-update.sh mainOr for latest release tag:
./scripts/receipts-update.sh releaseWhen to ask questions
Always ask the user before:
- Modifying
~/.claude/settings.json - Exporting logs to a remote Loki endpoint
- Changing redaction settings
interface:
display_name: "Receipts Control"
short_description: "Operate and query Receipts logs"
default_prompt: "Use $receipts-control to start the collector, tail Codex logs, or backfill history."
Related skills
Azure DeploySafely execute production deployments of already-prepared applications to Microsoft Azure.485k1.3kAzure ValidateRun deep pre-deployment checks on Azure configuration, infrastructure definitions, RBAC roles, and managed identities before pushing to production.485k1.3k
Github Actions DocsGet precise, docs-grounded answers about GitHub Actions workflows, syntax, security, and migration instead of relying on stale knowledge.275k72
Setup Pre CommitAutomatically run Prettier, type checking, and tests on every commit via Husky and lint-staged.170k199k
Deploy To VercelSafely turn any local project into a live Vercel preview with one instruction.99.3k29.7kVercel Cli With TokensDeploy projects to Vercel from agents and scripts using token authentication instead of interactive browser login.74.6k29.7kFAQ
What agents does Receipts observe?
Claude Code (via a PostToolUse hook), Codex CLI (JSONL session tailer), Gemini CLI (config guidance), and OpenCode (middleware example).
What does the skill ask before doing?
It always asks before modifying ~/.claude/settings.json, exporting logs to a remote Loki endpoint, or changing redaction settings.