Paperclip Create AgentCAUTION

The open-source app everyone uses to manage agents at work

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: paperclip-create-agent
description: >
  Create new agents in Paperclip with governance-aware hiring. Use when you need
  to inspect adapter configuration options, compare existing agent configs,
  draft a new agent prompt/config, and submit a hire request.
---

# Paperclip Create Agent Skill

Use this skill when you are asked to hire/create an agent.

## Preconditions

You need either:

- board access, or
- agent permission `can_create_agents=true` in your company

If you do not have this permission, escalate to your CEO or board.

## Workflow

### Choose the API transport

On **Paperclip Runner**, use the advertised Paperclip tools. Use `get_task_context`
and `list_agents` for identity and team context, then `search_api` to discover the
configuration, instruction-template, icon, and `agent-hires` endpoints used below.
Call the discovered operations with `call_api`; the server supplies company and
authentication context. Read the returned schemas before drafting the hire.

The shell examples below apply to adapters that receive `PAPERCLIP_API_URL` and
`PAPERCLIP_API_KEY`. Paperclip Runner does not supply those variables. Do not
search workspace files for a server address or credentials to recreate that path.
If `search_api` / `call_api` are unavailable, report that hiring requires the
operator to enable runner API tools for this company. Preserve the proposed hire
in the conversation; do not claim an agent was created or substitute a temporary
subagent for the requested permanent hire.

### 1. Confirm identity and company context

```sh
curl -sS "$PAPERCLIP_API_URL/api/agents/me" \
  -H "Authorization: Bearer $PAPERCLIP_API_KEY"
```

### 2. Discover adapter configuration for this Paperclip instance

```sh
curl -sS "$PAPERCLIP_API_URL/llms/agent-configuration.txt" \
  -H "Authorization: Bearer $PAPERCLIP_API_KEY"

# Then the specific adapter you plan to use, e.g. claude_local:
curl -sS "$PAPERCLIP_API_URL/llms/agent-configuration/claude_local.txt" \
  -H "Authorization: Bearer $PAPERCLIP_API_KEY"
```

### 3. Compare existing agent configurations

```sh
curl -sS "$PAPERCLIP_API_URL/api/companies/$PAPERCLIP_COMPANY_ID/agent-configurations" \
  -H "Authorization: Bearer $PAPERCLIP_API_KEY"
```

Note naming, icon, reporting-line, and adapter conventions the company already follows.

### 4. Choose the instruction source (required)

This is the single most important decision for hire quality. Pick exactly one path:

- **Exact template** — the role matches an entry in the template index. Use the matching file under `references/agents/` as the starting point.
- **Adjacent template** — no exact match, but an existing template is close (for example, a "Backend Engineer" hire adapted from `coder.md`, or a "Content Designer" adapted from `uxdesigner.md`). Copy the closest template and adapt deliberately: rename the role, rewrite the role charter, swap domain lenses, and remove sections that do not fit.
- **Generic fallback** — no template is close. Use the baseline role guide to construct a new `AGENTS.md` from scratch, filling in each recommended section for the specific role.

Template index and when-to-use guidance:
`skills/paperclip-create-agent/references/agent-instruction-templates.md`

Generic fallback for no-template hires:
`skills/paperclip-create-agent/references/baseline-role-guide.md`

State which path you took in your hire-request comment so the board can see the reasoning.

### 5. Discover allowed agent icons

```sh
curl -sS "$PAPERCLIP_API_URL/llms/agent-icons.txt" \
  -H "Authorization: Bearer $PAPERCLIP_API_KEY"
```

### 6. Draft the new hire config

- role / title / name
- icon (required in practice; pick from `/llms/agent-icons.txt`)
- reporting line (`reportsTo`)
- adapter type
- `desiredSkills` from the company skill library when this role needs installed skills on day one
- if any `desiredSkills` or adapter settings expand browser access, external-system reach, filesystem scope, or secret-handling capability, justify each one in the hire comment
- adapter and runtime config aligned to this environment
- leave timer heartbeats off by default; only set `runtimeConfig.heartbeat.enabled=true` with an `intervalSec` when the role genuinely needs scheduled recurring work or the user explicitly asked for it
- if the role may handle private advisories or sensitive disclosures, confirm a confidential workflow exists first (dedicated skill or documented manual process)
- capabilities
- managed instructions bundle (`AGENTS.md`) for adapters that support it; avoid durable `promptTemplate` config
- for coding or execution agents, include the Paperclip execution contract: start actionable work in the same heartbeat; do not stop at a plan unless planning was requested; leave durable progress with a clear next action; use child issues for long or parallel delegated work instead of polling; mark blocked work with owner/action; respect budget, pause/cancel, approval gates, and company boundaries
- instruction text such as `AGENTS.md` built from step 4; for local managed-bundle adapters, send this as top-level `instructionsBundle.files["AGENTS.md"]`. Do not set `adapterConfig.promptTemplate` or `bootstrapPromptTemplate` for new agents.
- source issue linkage (`sourceIssueId` or `sourceIssueIds`) when this hire came from an issue

### 7. Review the draft against the quality checklist

Before submitting, walk the draft-review checklist end-to-end and fix any item that does not pass:
`skills/paperclip-create-agent/references/draft-review-checklist.md`

### 8. Submit hire request

```sh
curl -sS -X POST "$PAPERCLIP_API_URL/api/companies/$PAPERCLIP_COMPANY_ID/agent-hires" \
  -H "Authorization: Bearer $PAPERCLIP_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "CTO",
    "role": "cto",
    "title": "Chief Technology Officer",
    "icon": "crown",
    "reportsTo": "<ceo-agent-id>",
    "capabilities": "Owns technical roadmap, architecture, staffing, execution",
    "desire

CAUTIONgrade B · trust 89/100 Install with care. The audit found things worth knowing before you trust its output.

What the source does

Filesystem

none-observed

Network

none-observed

Shell

none-observed

Dependencies

pinned

Secrets in source

none-found

Findings (4)

.claude/skills/company-creator

.claude/skills/paperclip

**OWASP API Top 10** — Broken Object-Level Authorization (BOLA/IDOR), Broken Authentication, Broken Object Property Level Authorization, Unrestricted Resource Consumption, Broken Function-Level Author

**LLM & agent security (OWASP LLM Top 10)** — Prompt Injection (direct and indirect), Insecure Output Handling, Training Data Poisoning, Model DoS, Supply Chain, Sensitive Information Disclosure, Inse

Gates applied: no_behavioural_pass.