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 bruhsb/paperclip-mcp --skill paperclip-close-epicgit clone --depth 1 https://github.com/bruhsb/paperclip-mcpWrote 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/bruhsb/paperclip-mcp/paperclip-close-epic)<a href="https://agentmods.dev/skills/bruhsb/paperclip-mcp/paperclip-close-epic"><img src="https://agentmods.dev/badge/skills/bruhsb/paperclip-mcp/paperclip-close-epic/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/bruhsb/paperclip-mcp/paperclip-close-epic"><img src="https://agentmods.dev/badge/skills/bruhsb/paperclip-mcp/paperclip-close-epic.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 | $0.00033 | $0.01281 |
| Opus 5 | $0.00016 | $0.00641 |
| Sonnet 5 | $0.00007 | $0.00256 |
| Haiku 4.5 | $0.00003 | $0.00128 |
Grade A, and why
paperclip-close-epic 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 11d 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
paperclip-close-epic
Verifies that every child issue of an epic is in done status, composes a structured closing summary, and transitions the epic to done. Produces a document artifact summarizing shipped work before closing.
When to use
Run this skill when:
- The Scrum Master heartbeat detects that all tracked children of an epic are
done. - A human operator or coordinator agent wants to formally close an epic and archive its outcomes.
- You are the Scrum Master and the heartbeat identified a candidate epic for closure.
Do not run this skill on an epic that has any child in todo, in_progress, in_review, or blocked. The skill will abort if that check fails.
Step 1 — Fetch the epic
paperclip_get_issue { issueId: "<epic-id>" }
Confirm the issue type is epic (or the equivalent parent-type in your Paperclip configuration). Record title, projectId, goalId, and status. If the epic is already done or cancelled, exit — nothing to do.
Step 2 — List all children
paperclip_list_issues does not accept a parentId filter. Use one of these strategies to find child issues:
Strategy A — filter by project, then check parentId in results (fastest for small projects):
paperclip_list_issues { projectId: "<epic-project-id>", limit: 100, offset: 0 }
Filter the returned issues client-side: issues.filter(i => i.parentId === epicId).
Strategy B — full-text search for the epic identifier:
paperclip_list_issues { q: "<PAP-N>", limit: 100, offset: 0 }
Strategy C — filter by goalId if the epic and all children share a goal:
paperclip_list_issues { goalId: "<epic-goal-id>", limit: 100, offset: 0 }
Then filter client-side by parentId. Use Strategy A unless the epic spans multiple projects.
If no children are found, log a warning and ask the operator before closing — an epic with no children may indicate a data problem.
Step 3 — Verify all children are done
For each child, check status === "done". If any child is not done:
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.
- 11d ago First seen · 152 lines · 33 tokens per session scan A 71d1f04ae7b3
paperclip-close-epic is a skill published in the GitHub repository bruhsb/paperclip-mcp (2 stars, last pushed 4mo ago), licensed MIT. It adds 33 tokens to every session and 1,281 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.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.