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-triage-inboxgit 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-triage-inbox)<a href="https://agentmods.dev/skills/bruhsb/paperclip-mcp/paperclip-triage-inbox"><img src="https://agentmods.dev/badge/skills/bruhsb/paperclip-mcp/paperclip-triage-inbox/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-triage-inbox"><img src="https://agentmods.dev/badge/skills/bruhsb/paperclip-mcp/paperclip-triage-inbox.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 | $0.00034 | $0.01341 |
| Opus 5.5 | $0.00014 | $0.00536 |
| Sonnet 5.5 | $0.00007 | $0.00268 |
| Haiku 4.5 | $0.00003 | $0.00134 |
Grade A, and why
paperclip-triage-inbox 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
paperclip-triage-inbox
Structured wake-up sequence for any IC agent. Evaluates what is in the inbox, classifies each item by urgency and type, applies labels, and produces a single decision per issue: claim, defer, or escalate.
When to use
Run this skill at the start of every agent session, before touching any issue. Do not skip it even if you believe you already know which issue to work on — the inbox may contain reassignments, escalations, or wake-reason mismatches that change the plan.
Step 1 — Confirm identity
paperclip_get_me
Record agentId, role, and urlKey. These are needed for branch naming and @-mention targeting throughout the session.
Step 2 — Read the inbox
paperclip_get_inbox
The response is a list of issues currently assigned to this agent. If the list is empty, exit cleanly — there is nothing to claim. Do not poll or retry.
Step 3 — Fetch heartbeat context
paperclip_get_heartbeat_context
This surfaces PAPERCLIP_WAKE_REASON and PAPERCLIP_TASK_ID. Cross-reference the wake reason against the inbox items. If the wake reason references an issue that is NOT in the inbox, post a mismatch comment (see Error Handling) and exit.
Step 4 — Classify each inbox item
For each issue returned in Step 2, fetch its full record:
paperclip_get_issue { issueId: "<id>" }
Classify using the following decision matrix:
| Condition | Decision |
|---|---|
Status is todo, assigned to me, wake reason matches |
Claim |
Status is in_review but I am not QA |
Escalate — this should not be in my inbox |
Status is blocked |
Defer — post a note, do not claim |
Status is done or cancelled |
Skip — stale assignment, no action |
Priority is urgent and no other agent is active |
Claim first among all claimable items |
| Multiple claimable items | Claim highest priority first, defer the rest |
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 · 149 lines · 34 tokens per session scan A d74538102afa
paperclip-triage-inbox is a skill published in the GitHub repository bruhsb/paperclip-mcp (2 stars, last pushed 6mo ago), licensed MIT. It adds 34 tokens to every session and 1,341 once invoked, about $0.0001 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
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.
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.
qa-project-bootstrap
Onboard a new QA engineer to an existing codebase, or audit an existing test architecture. Produces a 30-day ramp plan: codebase orientation, framework walkthrough, test architecture audit, mentorship pairing, and first-test guidance. Use when: "QA onboarding," "new tester," "ramp up," "test architecture audit,"…
remove
Remove a deployed framework or addon from the current workspace.