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.
npx skills add emaraschio/cursor-commands --skill agent-work-receiptgit clone --depth 1 https://github.com/emaraschio/cursor-commandsWrote 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/emaraschio/cursor-commands/agent-work-receipt)<a href="https://agentmods.dev/skills/emaraschio/cursor-commands/agent-work-receipt"><img src="https://agentmods.dev/badge/skills/emaraschio/cursor-commands/agent-work-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.
<a href="https://agentmods.dev/skills/emaraschio/cursor-commands/agent-work-receipt"><img src="https://agentmods.dev/badge/skills/emaraschio/cursor-commands/agent-work-receipt.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 | $0.00060 | $0.01155 |
| Opus 5.5 | $0.00024 | $0.00462 |
| Sonnet 5.5 | $0.00012 | $0.00231 |
| Haiku 4.5 | $0.00006 | $0.00115 |
Grade A, and why
agent-work-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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent work receipt
Role
You produce a conservative agent work receipt for work already completed in the current session. You account for what actually landed, not what was discussed, drafted, or abandoned. You do not start new implementation, commits, or destructive commands in the same turn.
When to use
Use when the user invokes /agent-work-receipt, asks for a work receipt, or wants honest accountability for agent-assisted work after a session. For planning before autonomous work, use define-agent-goal. For code quality on diffs, use light-review-existing-diffs.
Conservative charter
Be conservative. Do not count drafts, ideas, or unused output as completed work.
Workflow
Run phases in order. Do not publish the receipt until evidence is gathered.
Phase 0: Intake
- Parse a scope hint from the user message (e.g. "receipt for the refactor in service-a").
- If no scope hint, default to the full session.
- If the user invokes mid-task with no finished work yet, scope to partial work only or ask whether to wait. Do not hallucinate completion.
Phase 1: Evidence
Gather read-only evidence:
- Conversation: what the user asked for, what the agent actually did, what was rejected or abandoned
- Git (when a repo is present):
git status,git diff,git logto ground landed artifacts - Files: only artifacts explicitly created, edited, committed, or merged in scope
Do not treat uncommitted explorations, reverted edits, or failed tool runs as finished output.
Phase 2: Inventory
List only landed artifacts in scope:
- Files written or modified that remain in the tree
- Commits, branches, or PRs created
- Docs, plans, or configs delivered to the user
Explicitly note what you exclude: brainstorms, unused drafts, abandoned paths, tool errors, reverted work.
Phase 3: Estimates
Provide human baseline and agent-assisted time as ranges or point estimates. Label both clearly as estimates, not measured facts. The user may correct in follow-up.
What ships with it
3 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.
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.
- 1mo ago First seen · 125 lines · 60 tokens per session scan A d07090b75479
agent-work-receipt is a skill published in the GitHub repository emaraschio/cursor-commands (9 stars, last pushed 20d ago), licensed MIT. It adds 60 tokens to every session and 1,155 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 2026-08-31.
Other skills, from other repositories
cursor-delegate
Delegate bounded light-to-medium implementation, investigation, documentation, configuration, testing, and tooling work to Cursor Bridge after the primary agent owns direction and risk boundaries. Also use when the user explicitly asks to create, keep, continue, inspect, or close the same Cursor execution session…
audit-accomplishments
Use when preparing a performance self-reflection, midyear or annual review, promotion packet, or brag document; when asked to collect, mine, gather, or summarize your accomplishments, contributions, or impact over a period; or when assembling cited evidence of work done across GitHub, Jira, Notion, Slack, and local…
start-day
Use at the start of a workday or when the user says "start my day", "good morning", "/start-day", "morning", "what should I work on today", or wants a catch-up on what happened while they were away. Use when the user wants a short ranked list of what to tackle today.
complete-everything
Closure mode for one approved plan: finish every open item and connected deferral, verify each acceptance criterion, require completion-judge PASS. Use when "complete everything", "don't defer", "fix out of scope too", or a plan was falsely marked done.
housekeep-files
Copy-not-move organizer for document trees: hash inventory, dry run, labeled copies, search catalog, verify every source survived. Use when "organize my Downloads", "sort my company folders", or "file my receipts". Repo cleanup → workflow-housekeep.
housekeep-backlog
Inventory parked work — unfinished plans, deferred phases, TODO/FIXME, skipped tests, open findings — into a living BACKLOG.md that diffs new/done/stale. Use when "what's left behind", "inventory TODOs", or "consolidate the backlog".