Paperclip is a Node.js server and React application for coordinating AI agents as a business team, with goals, organizational roles, budgets, governance, and work tracking in one interface. It is used by people managing multiple agents or autonomous agent organizations across tools such as OpenClaw, Claude Code, Codex, and Cursor. The catalogue includes skills, agents, an MCP add-on, and an instruction for working with Paperclip.
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 paperclipai/paperclip --skill qa-acceptancegit clone --depth 1 https://github.com/paperclipai/paperclipWrote 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/paperclipai/paperclip/qa-acceptance)<a href="https://agentmods.dev/skills/paperclipai/paperclip/qa-acceptance"><img src="https://agentmods.dev/badge/skills/paperclipai/paperclip/qa-acceptance/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/paperclipai/paperclip/qa-acceptance"><img src="https://agentmods.dev/badge/skills/paperclipai/paperclip/qa-acceptance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 18 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00038 | $0.00833 |
| Opus 5.5 | $0.00015 | $0.00333 |
| Sonnet 5.5 | $0.00008 | $0.00167 |
| Haiku 4.5 | $0.00004 | $0.00083 |
Grade A, and why
qa-acceptance 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Acceptance
Write acceptance criteria that a reviewer can run against the running app and decide pass or fail without asking the author. The criteria are the contract — automated tests cover correctness, QA covers feature-level behavior.
When to use
- A feature change is heading to QA and needs a written validation plan.
- A reviewer is asked to verify a PR that touches user-visible behavior.
- An incident postmortem requires a regression check before reopen-prevention.
- A release candidate needs a pre-cut smoke pass.
When not to use
- The change is unit-test-only (utility refactor, internal naming). Acceptance criteria are unnecessary churn.
- You are asked to write tests against API contracts. Use contract testing, not feature QA.
Acceptance criteria format
Each criterion is a single, independently-verifiable statement:
- **Given** <starting state>, **when** <action>, **then** <observable outcome>.
Example:
- **Given** a CSV export with 0 rows, **when** the user clicks Export, **then** the file downloads with only the header row and the UI shows "Exported 0 rows".
Avoid criteria that combine multiple whens or thens. Split them.
What every plan must cover
- Golden path. The most common successful flow, end to end.
- Empty and minimum states. Zero items, one item, missing optional inputs.
- Boundary inputs. Max length strings, max numeric values, unicode, RTL text where applicable.
- Error states. Network failure, permission denied, validation failures, conflict (409), not found (404).
- Concurrency and ordering. Two users acting at once, race against background jobs, refresh during mutation.
- Performance envelope. The largest realistic input the change must handle without UI hangs or timeouts.
- Backward compatibility. Existing data, existing URLs, persisted user preferences continue to work.
- Telemetry and audit. Events, logs, or activity entries the change is supposed to emit.
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 · 94 lines · 38 tokens per session scan A c631b437ab26
qa-acceptance is a skill published in the GitHub repository paperclipai/paperclip (106,591 stars, last pushed today), licensed MIT. It adds 38 tokens to every session and 833 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 2026-08-30.
Other skills, from other repositories
frontend-manual-testing
Use when the task changes anything a user sees in a web app - booting it, driving flows with the browser tools, the four-width check, console/network/keyboard checks and the visual checklist.
accessibility-check
Use when a task changes any screen, form, dialog, menu or control - Lighthouse/axe scan of the changed screens, a keyboard walk, and the thresholds that fail a task.
performance-smoke-testing
Use when a criterion mentions speed or limits, or the change touches a list, query, endpoint or page that could get slower - timing loops, the N-vs-10N data check and Lighthouse on a production build.
qa-verify-before-verdict
Use before any reviewcriterion approval or column move - the evidence each verdict needs, how to treat skipped, blocked and intermittent cases, and which exit a blocker takes.
test-environment-selection
Use before booting anything - choosing local (starttaskpreview or a workspace boot), the task's preview or stage, confirming the build is the PR head, and what to do when nothing can run.
backend-manual-testing
Use when the task touches a backend API, database or worker - booting it from the task branch, driving real requests and verifying side effects (DB rows, outbound calls, logs) as evidence.