paperclip-audit-approvals

paperclip-audit-approvals is a skill for Claude Code, Codex from bruhsb/paperclip-mcp. It costs 38 tokens per session (1,383 once invoked), scanned A, original, MIT.

A review procedure for an agent responsible for deciding on pending approvals. It requires checking each approval, reviewing its comments, and choosing to approve, reject with requested changes, or escalate it.

In plain words
What is it for?
Use it to process a queue of pending approvals, confirm the current agent’s role, inspect approval records, and route unauthorized or governance-related items correctly.
Why use it?
It prevents approval requests from being handled without checking their details or the reviewer’s authority. Board-level decisions must be escalated instead of decided by one approver.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to process a queue of pending approvals, confirm the current agent’s role, inspect approval records, and route unauthorized or governance-related items correctly.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bruhsb/paperclip-mcp/paperclip-audit-approvals
Install

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.

Any agent
npx skills add bruhsb/paperclip-mcp --skill paperclip-audit-approvals
Clone the repo
git clone --depth 1 https://github.com/bruhsb/paperclip-mcp

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for paperclip-audit-approvals

README.md
[![agentmods](https://agentmods.dev/badge/skills/bruhsb/paperclip-mcp/paperclip-audit-approvals/github.svg)](https://agentmods.dev/skills/bruhsb/paperclip-mcp/paperclip-audit-approvals)
Your own site
<a href="https://agentmods.dev/skills/bruhsb/paperclip-mcp/paperclip-audit-approvals"><img src="https://agentmods.dev/badge/skills/bruhsb/paperclip-mcp/paperclip-audit-approvals/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.

agentmods 80×15 button for paperclip-audit-approvals

Your own site · 80×15
<a href="https://agentmods.dev/skills/bruhsb/paperclip-mcp/paperclip-audit-approvals"><img src="https://agentmods.dev/badge/skills/bruhsb/paperclip-mcp/paperclip-audit-approvals.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,383 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00038 $0.01383
Opus 5 $0.00019 $0.00691
Sonnet 5 $0.00008 $0.00277
Haiku 4.5 $0.00004 $0.00138

Measured 12d ago against content hash 5679a9c91074, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

paperclip-audit-approvals 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 12d 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.

skills/paperclip-audit-approvals/SKILL.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

paperclip-audit-approvals

Walks every pending approval assigned to the current agent, retrieves the full approval record and its comments, applies a structured review checklist, then issues a single decision per approval: approve, reject (with revision request), or escalate.

When to use

Run this skill when:

  • You are an approver agent (CEO, CTO, or a designated board reviewer) and you wake on an @-mention that references a pending approval.
  • The Scrum Master has flagged an orphaned approval that has been pending beyond its SLA.
  • A human operator asks you to clear a queue of pending approvals.

Board-only warning: Some approvals are board-level governance decisions (agent hires, budget increases, architecture changes). If the approval record contains any of the labels type:governance or type:board-decision, do not approve or reject unilaterally — escalate to the board channel and exit.

Step 1 — Confirm identity

paperclip_get_me

Record agentId and role. Only proceed if your role is authorized to approve the items in the queue. If you are not the designated approver for an item, skip it and post a routing comment (see Error Handling).

Step 2 — List pending approvals

paperclip_list_approvals  { status: "pending" }

Filter the result to approvals where approverId === <your-agentId> or approverRole === <your-role>. If none match, exit — no work to do.

Step 3 — Process each approval

For each matching approval, run the following sub-sequence:

3a — Fetch the full approval record
paperclip_get_approval  { approvalId: "<id>" }

Record: title, description, submittedBy, createdAt, linkedIssueId (if any), labelIds.

3b — Fetch approval comments
paperclip_list_approval_comments  { approvalId: "<id>" }

Look for prior reviewer notes. If a previous approver has already rejected this item and the resubmission did not address the stated concerns, note this — it affects the decision.

Read the full file on GitHub · 158 lines

Changes

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.

  1. 12d ago First seen · 158 lines · 38 tokens per session scan A 5679a9c91074

Subscribe to this mod's changes

paperclip-audit-approvals is a skill published in the GitHub repository bruhsb/paperclip-mcp (2 stars, last pushed 4mo ago), licensed MIT. It adds 38 tokens to every session and 1,383 once invoked, about $0.0002 per session on Opus 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens