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.
Borrowing it
Nothing to install: this file belongs to paperclipai/paperclip. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/paperclipai/paperclip/master/.agents/skills/terminal-bench-loop/SKILL.mdgit 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/terminal-bench-loop)<a href="https://agentmods.dev/skills/paperclipai/paperclip/terminal-bench-loop"><img src="https://agentmods.dev/badge/skills/paperclipai/paperclip/terminal-bench-loop/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/terminal-bench-loop"><img src="https://agentmods.dev/badge/skills/paperclipai/paperclip/terminal-bench-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 3 findings, 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 MCP Rug Pull · line 91 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
- medium Excessive Agency · line 191 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.
- medium Agent Snooping · line 223 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00054 | $0.05451 |
| Opus 5.5 | $0.00022 | $0.02180 |
| Sonnet 5.5 | $0.00011 | $0.01090 |
| Haiku 4.5 | $0.00005 | $0.00545 |
Grade A, and why
terminal-bench-loop 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 — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Terminal-Bench Loop
A repeatable operating skill for driving one Terminal-Bench problem to a passing smoke through Paperclip, with explicit issue topology, bounded runs, board-gated product fixes, and worktree continuity.
This skill is operational + diagnostic, not engineering. It coordinates issues, artifacts, and approvals around a Terminal-Bench loop. It does not authorize code changes — every accepted product fix lands as a separate implementation child issue after a board confirmation.
Canonical execution model: read doc/execution-semantics.md before starting a loop or moving any loop issue. Every loop issue must rest in a state the doc allows: terminal (done/cancelled), explicitly live (active run / queued wake), explicitly waiting (in_review with participant/interaction/approval), or explicit recovery/blocker (blocked with blockedByIssueIds and a named owner).
When to use
Trigger on an assignment whose title or body matches any of:
- "run Terminal-Bench in a loop", "loop <task-name> through Paperclip"
- "drive Terminal-Bench fix-git", "iterate on Terminal-Bench until it passes"
- "Terminal-Bench smoke loop", "bench loop", "smoke loop on <task-name>"
- An attached link to a Terminal-Bench loop parent issue, plus a request to do another iteration
Also use when the user hands you an existing top-level loop issue and asks for the next iteration, diagnosis, or rerun.
When NOT to use
- The assignment is to build or change
paperclip-benchitself (Harbor adapter, wrapper, telemetry). Use normal engineering flow on that repo. - The assignment is to submit a benchmark result for ranking. This skill produces smoke/non-comparable runs by design — escalate full-suite or comparable runs to BenchmarkQualityManager.
- The assignment is a normal Paperclip product bug not surfaced by a Terminal-Bench loop. Use normal investigation.
- You have not been granted permission to install or assign company skills, and the asker actually wants library mutation. Hand that step to an authorized skill-library owner.
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 · 229 lines · 54 tokens per session scan A 4acbe1f61931
terminal-bench-loop is a skill published in the GitHub repository paperclipai/paperclip (107,044 stars, last pushed today), licensed MIT. It adds 54 tokens to every session and 5,451 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
deep-reasoning
Structured multi-step reasoning tool for complex problem solving with branching, hypothesis testing, and evidence tracking.
agent-benchmark-suite
Agent skill for benchmark-suite - invoke with $agent-benchmark-suite.
Verification & Quality Assurance
Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.
agent-production-validator
Agent skill for production-validator - invoke with $agent-production-validator.
agent-tester
Agent skill for tester - invoke with $agent-tester.
agent-implementer-sparc-coder
Agent skill for implementer-sparc-coder - invoke with $agent-implementer-sparc-coder.