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 skills/omnigent-ai/omnigent/polly-e2e-devnpx skills add omnigent-ai/omnigent --skill polly-e2e-devgit clone --depth 1 https://github.com/omnigent-ai/omnigentWrote 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/omnigent-ai/omnigent/polly-e2e-dev)<a href="https://agentmods.dev/skills/omnigent-ai/omnigent/polly-e2e-dev"><img src="https://agentmods.dev/badge/skills/omnigent-ai/omnigent/polly-e2e-dev.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 | $0.00180 | $0.03281 |
| Opus 5 | $0.00090 | $0.01640 |
| Sonnet 5 | $0.00036 | $0.00656 |
| Haiku 4.5 | $0.00018 | $0.00328 |
Grade E, and why
polly-e2e-dev scanned grade E with 3 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
SID=$(curl -s "$SERVER/v1/sessions?kind=default&order=desc&limit=1" | python -c "import sys,json;print(json.load(sys.stdin)['data'][0]['id'])") Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
force-push / `rm -rf /`), `spawn_bounds` (cap dispatches per turn), Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
SID=$(curl -s "$SERVER/v1/sessions?kind=default&order=desc&limit=1" | python -c "import sys,json;print(json.load(sys.stdin)['data'][0]['id'])") How it starts
The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
polly orchestrator: end-to-end CUJ dev & testing
polly (examples/polly/) is a multi-agent coding orchestrator: a
claude-sdk "brain" that writes no code itself and delegates everything to three
coding sub-agents — claude_code (claude-native), codex (codex-native), and
pi (headless, multi-model). Its critical user journeys are orchestration
behaviors, not single-turn answers:
- roster preflight — first turn runs
command -v claude codex pi, routes only to workers whose CLI resolved. - investigate — read-only work fanned to
explore/searchsub-agents; synthesize from their reports. - fanout — independent tasks, each in its own git worktree + sub-agent, each opening its own PR.
- cross-review — an implementer's diff is verified by a different-vendor sub-agent (diff + contract only); blocking issues become fix-tasks.
- plan gate / inbox — pull the human in at the plan gate; supervise via the inbox + autowake, never busy-poll.
- guardrails (
omnigent.inner.nessie.policies) —blast_radius(deny force-push /rm -rf /),spawn_bounds(cap dispatches per turn),headless_subagent_purpose_guard(every dispatch needsargs.purpose).
This skill tests those CUJs two ways. Use both — they cover different things:
| Half | What it proves | Needs |
|---|---|---|
Mock loop (polly_cuj.py) |
The substrate/mechanics — the brain is scripted, so this proves bundle load, server-side policy resolution, bridged sys_* tool dispatch, the guardrail DENYs, and fan-out — deterministically, with no creds |
nothing (mock LLM) |
| Live recipe | polly's judgment — does the real brain preflight, decompose, delegate, cross-review, and pull in the human correctly | real claude/codex/pi + model creds + network |
Like the sibling harness skills, turns run from your current checkout (
omni run <bundle> --server <url>= local runner + remote server), so testing exercises exactly the code you're on.
What ships with it
1 file 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.
- 4d ago First seen · 232 lines · 180 tokens per session scan E 2b077b2eb406
polly-e2e-dev is a skill published in the GitHub repository omnigent-ai/omnigent (9,658 stars, last pushed today), licensed Apache-2.0. It adds 180 tokens to every session and 3,281 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it E with 3 findings (downloads and executes remote code, recursive force delete, 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
ml-debug
Use when something is failing in ML/AI work — OOM, NaN, divergence, crashes, bad throughput, wrong outputs, dependency conflicts.
ml-plan
Use when the user wants an implementation plan, architecture design, or multi-step ML pipeline — "build X", "implement X", "design X", "set up X".
ml-research
Use when the user wants to understand an ML/AI topic, compare approaches, or survey framework capabilities — "how does X work?", "compare X vs Y".
ml-iterate
Use when the user is stuck, needs ranked next steps, or wants alternatives after initial experiments — "I tried X and got Y, what next?".
using-superml
Use when starting any conversation involving ML/AI — establishes how to use Leeroopedia KB tools and workflow skills.
ml-verify
Use when the user wants to verify code, config, or math before running — or proactively before any expensive training job or deployment.