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 agentmods add commands/kevinzai/commander/ccc-paperclipgit clone --depth 1 https://github.com/KevinZai/commanderWrote 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/commands/kevinzai/commander/ccc-paperclip)<a href="https://agentmods.dev/commands/kevinzai/commander/ccc-paperclip"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc-paperclip.svg" alt="Measured on agentmods" 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 | $0.00019 | $0.00336 |
| Opus 5 | $0.00010 | $0.00168 |
| Sonnet 5 | $0.00004 | $0.00067 |
| Haiku 4.5 | $0.00002 | $0.00034 |
Grade C, and why
ccc-paperclip scanned grade C with 2 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 today.
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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -s "http://localhost:3110/api/companies/{YOUR_COMPANY_ID}/issues?assigneeId=AGENT_UUID&stateType=started" | python3 -m json.tool Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s "http://localhost:3110/api/companies/{YOUR_COMPANY_ID}/issues?assigneeId=AGENT_UUID&stateType=started" | python3 -m json.tool What it actually says
/paperclip — Paperclip Task Management
Query and update Paperclip tasks from Claude Code.
Common Operations
List my assigned issues
curl -s "http://localhost:3110/api/companies/{YOUR_COMPANY_ID}/issues?assigneeId=AGENT_UUID&stateType=started" | python3 -m json.tool
Update issue status
curl -s -X PATCH "http://localhost:3110/api/issues/{ISSUE_ID}" \
-H "Content-Type: application/json" \
-d '{"status": "done"}'
Add comment to issue
curl -s -X POST "http://localhost:3110/api/issues/{ISSUE_ID}/comments" \
-H "Content-Type: application/json" \
-d '{"body": "Completed: <summary>"}'
Search issues
curl -s "http://localhost:3110/api/companies/{YOUR_COMPANY_ID}/issues?query=search+term" | python3 -m json.tool
Agent UUIDs (for assignee filtering)
Check ~/your-project/agent-directory.md for the full agent→UUID map.
Notes
- Paperclip runs on localhost:3110, no auth required (local_trusted mode)
- Company ID: {YOUR_COMPANY_ID} (check via
/api/companies) - All inter-agent work should reference a Paperclip issue
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.
- today First seen · 42 lines · 19 tokens per session scan C 44d0bf8c1d80
ccc-paperclip is a command published in the GitHub repository KevinZai/commander (6 stars, last pushed yesterday), licensed MIT. It adds 19 tokens to every session and 336 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other commands, from other repositories
whats-next
Show current project status and suggest next steps.
specmanager-build
Build one phase of a SpecManager feature's plan via the builder subagent. Stops at the phase boundary; never advances.
execute
Execute the next available tracked task with TDD, pre-commit validation, PR creation, AI code review, and issue tracker bridge sync.
phase
Orchestrate a full roadmap phase. Designs features, imports to tracker, creates issues, then executes.
roadmap
Generate or update a per-release roadmap from the PRD and analysis documents. Triages features, groups into phases, and produces a structured roadmap.
dashboard
Compact visual progress dashboard with progress bar, task table, dependency graph, and active/blocked/next status.