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 mrobinson2/AzureAgentForge --skill agent-delegategit clone --depth 1 https://github.com/mrobinson2/AzureAgentForgeWrote 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/mrobinson2/azureagentforge/agent-delegate)<a href="https://agentmods.dev/skills/mrobinson2/azureagentforge/agent-delegate"><img src="https://agentmods.dev/badge/skills/mrobinson2/azureagentforge/agent-delegate/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/mrobinson2/azureagentforge/agent-delegate"><img src="https://agentmods.dev/badge/skills/mrobinson2/azureagentforge/agent-delegate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 288 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Data Exfiltration · line 321 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00111 | $0.03987 |
| Opus 5.5 | $0.00044 | $0.01595 |
| Sonnet 5.5 | $0.00022 | $0.00797 |
| Haiku 4.5 | $0.00011 | $0.00399 |
Grade A, and why
agent-delegate scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
## Use the helper, not raw curl How it starts
The opening of the file, as written. The whole thing — 372 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Delegate or Coordinate Tasks via PaperClip Child Issues
A comment that says "I delegated this to X" is not delegation. The other agent has no way to see your comment. The only way to delegate is to create a real PaperClip issue with that agent's
assigneeAgentId.
This skill covers two patterns:
- Single-agent delegation — one parent task, one child issue, one specialist.
- Coordination — one parent task, two or more child issues, multiple specialists.
Both patterns use the same API and the same helper script.
Runtime environment
Required environment variables
| Variable | Purpose |
|---|---|
PAPERCLIP_API_KEY |
Bearer token for the PaperClip API (ctx.authToken for embedded Orchestrator; automation JWT for standalone Hermes) |
PAPERCLIP_BASE_URL |
PaperClip API base URL — varies by runtime (see table below) |
PAPERCLIP_ORIGIN |
Origin header value sent with every API request |
PAPERCLIP_COMPANY_ID |
PaperClip company UUID (default: 00000000-0000-0000-0000-000000000000) |
PAPERCLIP_API_KEY is required. If the others are unset the helper defaults apply:
PAPERCLIP_BASE_URL→http://localhost:3099(direct backend; correct for PaperClip-embedded Orchestrator)PAPERCLIP_ORIGIN→http://localhost:3100PAPERCLIP_COMPANY_ID→00000000-0000-0000-0000-000000000000
Helper path — resolve before first use each session
The helper script lives in different locations depending on which runtime the agent is executing in. Always discover the path dynamically; never hardcode it.
DELEGATE_HELPER=""
for _p in \
"/paperclip/.hermes/skills/playbooks/agent-delegate/scripts/pc-delegate.sh" \
"/app/skills/playbooks/agent-delegate/scripts/pc-delegate.sh" \
"/opt/data/skills/playbooks/agent-delegate/scripts/pc-delegate.sh"; do
if [ -x "$_p" ]; then DELEGATE_HELPER="$_p"; break; fi
done
[ -z "$DELEGATE_HELPER" ] && { echo "ERROR: pc-delegate.sh not found in any known location" >&2; exit 2; }
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 372 lines · 111 tokens per session scan A 10d084dd0ba5
agent-delegate is a skill published in the GitHub repository mrobinson2/AzureAgentForge (24 stars, last pushed yesterday), licensed MIT. It adds 111 tokens to every session and 3,987 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
company-employee
The protocol every employee of a PenguinHarness organization follows — read the handbook first, act on [orgtrigger] work runs, schedule tickets from the desk session and do the work in ticket sessions, block instead of idling, ask the board in the all-hands channel before anything heavy, costly, irreversible or…
company-ceo
Run a PenguinHarness organization as its CEO — turn the mission into a ticket tree, hire HR and finance first, partition the shared workspace, schedule the calendar, open a channel per stream, review tickets and report to the board in the all-hands channel.
company-hr
Run HR for a PenguinHarness organization — guarantee every employee has an enabled calendar event, hire and offboard employees (channels included), evaluate and improve them (with the default-rsi-toolkit plugin's agent-optimization skill), and keep the handbook's role conventions current.
company-mirror
Run a PenguinHarness organization that mirrors a real company — one digital twin per real colleague, each twin's desk bound to that colleague's chat bot, twins answering what the handbook already knows and relaying the rest to one another instead of hiring, scheduling and filing tickets.
company-setup
Create a company-mode organization together with the user — collect its id, name, mission, shared workspace, model and CEO budget one question at a time, confirm the whole thing in one summary, then run penguin org create and hand the user over to company mode.
handoff
Hand the work discussed in this session (every message the user wrote, your replies quoted, where the code is) to another person, by email or straight to their ConnectOnion agent, after removing secrets and getting the user's approval of the exact text; and receive one from a pasted prompt that carries a coh1., coh2.…