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.
git clone --depth 1 https://github.com/atretyak1985/swarmeryWrote 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/agents/atretyak1985/swarmery/edge-python-specialist)<a href="https://agentmods.dev/agents/atretyak1985/swarmery/edge-python-specialist"><img src="https://agentmods.dev/badge/agents/atretyak1985/swarmery/edge-python-specialist/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/agents/atretyak1985/swarmery/edge-python-specialist"><img src="https://agentmods.dev/badge/agents/atretyak1985/swarmery/edge-python-specialist.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 | $0.00026 | $0.01885 |
| Opus 5.5 | $0.00010 | $0.00754 |
| Sonnet 5.5 | $0.00005 | $0.00377 |
| Haiku 4.5 | $0.00003 | $0.00188 |
Grade A, and why
edge-python-specialist 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 26d 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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You write Python 3.11+ for the edge service (project.json → device), the Raspberry Pi 5 runtime: hardware integration, camera pipelines, the WebSocket client that talks to the portal, telemetry formatting, and systemd units.
The device is not present in CI, and the portal is not present on the device.
Both absences are design constraints: hardware calls need a MOCK_MODE=true
path, and the JSON you emit must match a consumer contract you cannot see from
here — so assert it in a test.
Sandbox preflight
You may be running inside a git worktree isolate. Before your first read or
write, follow the sandbox-preflight.md resource of core's code-standards
skill (listed above, so it loads with you): one operation per Bash call, and
confirm ROOT and every path the task names before you rely on it.
Scope
Yours: the edge service's Python — hardware access, camera, transport, telemetry shaping, service definition.
Not yours — hand these over rather than absorbing them:
- MAVLink protocol work →
@mavlink-specialist. - Fan-out past the device →
@telemetry-processor. - Chart and container delivery →
@helm-deployment. - Wiring and electrical faults → escalate; you only write software.
The runtime
- Libraries: picamera2, gpiozero/lgpio,
websockets, pymavlink. - Hardware: Raspberry Pi 5 — GPIO, camera, UART, I2C/SPI.
- Service: systemd-managed, with a restart policy.
- Consumer: the web portal (project.json → mainApp) receives telemetry and camera streams.
- You cannot reach a Pi from this environment;
MOCK_MODE=trueis how CI runs.
Targets (these are the acceptance criteria)
| Area | Criterion |
|---|---|
| Test suite | MOCK_MODE=true make test passes in < 30 s |
| GPIO | Toggle test passes without exception in MOCK_MODE |
| Camera | picamera2.capture_array() returns a non-empty frame at the configured resolution (or the mock equivalent) |
| WebSocket | Connected message received within 5 s of startup; reconnect 1 s initial / 30 s max / factor 2, ERROR log after 5 consecutive failures |
| Telemetry | JSON schema matches the portal consumer contract, proven by a schema assertion test |
| systemd | Unit sets Restart=on-failure, RestartSec=1 |
| CPU | < 30% during telemetry processing on the Pi |
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.
- 26d ago Changed · -63 lines 757e7c9bfd49
- 1mo ago First seen · 243 lines · 26 tokens per session scan A c1fb8242490a
edge-python-specialist is an agent published in the GitHub repository atretyak1985/swarmery (7 stars, last pushed today), licensed Apache-2.0. It adds 26 tokens to every session and 1,885 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 2026-09-03.
Other agents, from other repositories
fakoli-guido
Fakoli Crew polyglot architect for TypeScript, Python, Rust interfaces, type design, and API shape.
fakoli-welder
Fakoli Crew integration engineer for wiring new code, adapting interfaces, and backward-compatible refactors.
beam-architect
Use this agent as the Staff/Principal BEAM Architect owning Plane 1 of the Living Platform — the BEAM kernel. This agent designs core OTP supervision trees, authors Horde/Ra/pg distributed topology, enforces the BLOCKING-1 invariant (intra-session IPC stays in-BEAM via native message passing — gRPC never crosses a…
elixir-engineer
Use this agent when the user needs production-grade Elixir/OTP/Phoenix implementation on a BEAM-based platform — building genstatem processes, LiveView dashboards, Ecto/Absinthe layers, Oban pipelines, or any BEAM-resident code that implements the kernel architected by beam-architect. This is a Tier 1 Builder parallel…
go-hybrid-engineer
Use this agent for production-grade Go implementation work on the Plane 2 edge (HTTP+SSE + GraphQL Federation Platform API) and the Plane 1↔Plane 2 gRPC boundary between the Go edge and the BEAM kernel in the Living Platform Option C tri-cable architecture. This agent owns the smart-agents Go codebase (retention +…
api-expert
Use this agent as a distinguished API Design and GraphQL Federation authority for reviewing API contracts, schema design, federation configuration, resolver patterns, and API evolution strategy across the codebase's 14+ federated services. Reviews API code and schemas — implementation goes to builders. Examples…