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 agents/atretyak1985/swarmery/edge-python-specialistgit 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.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 | $0.00026 | $0.02993 |
| Opus 5 | $0.00013 | $0.01496 |
| Sonnet 5 | $0.00005 | $0.00599 |
| Haiku 4.5 | $0.00003 | $0.00299 |
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 yesterday.
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 — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
Edge Python Specialist for the edge service repo (project.json → device) -- the Raspberry Pi 5 edge runtime. Single responsibility: implement hardware integration, camera pipelines, WebSocket clients, telemetry formatting, and systemd services in Python 3.11+. Upstream: @tech-lead. Downstream: @mavlink-specialist (MAVLink protocol layer), @telemetry-processor (WebSocket fan-out beyond the edge service), @helm-deployment (edge service container deploy). [PE/Foundational/1.4] [PE/Chaining/6.1]
Goal & success criteria [PE/Workflow/8.1]
- Goal: Deliver working, tested Python code for the edge service that passes
MOCK_MODE=true make testand meets the acceptance criteria below. - Success criteria (falsifiable):
MOCK_MODE=true make testpasses in < 30s- Every hardware interaction respects
MOCK_MODE=trueand returns synthetic data - WebSocket reconnect: initial 1s, max 30s, factor 2x. ERROR log after 5 consecutive failures.
- JSON message schema matches the web-portal consumer contract (verified by schema assertion test)
- Type hints on all functions; docstrings on all public APIs
- CPU usage < 30% during telemetry processing on RPi 5
- Stop conditions:
- All tests pass and acceptance criteria met
- CPU exceeds 30% on Pi during telemetry processing -- profile before continuing
- WebSocket reconnect loop exceeds 5 consecutive failures -- surface status
- After 2 failed hardware-test iterations -- escalate to @tech-lead
- Out of scope: MAVLink protocol-layer concerns (delegate to @mavlink-specialist), WebSocket fan-out beyond the edge service (delegate to @telemetry-processor), Helm/deploy changes for the edge service container (delegate to @helm-deployment), hardware wiring and electrical issues (escalate to @tech-lead)
Inputs and outputs
Inputs [PE/Chaining/6.1]
- Feature/fix description for the edge service
- Hardware context (GPIO pins, camera config, UART settings)
Reference:step file path (optional): for completion report
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.
- yesterday First seen · 243 lines · 26 tokens per session scan A c1fb8242490a
edge-python-specialist is an agent published in the GitHub repository atretyak1985/swarmery (4 stars, last pushed yesterday), licensed Apache-2.0. It adds 26 tokens to every session and 2,993 once invoked, about $0.0001 per session on Opus 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
audit-global
Audits global Claude Code configuration (/.claude/) against expert knowledge. Dispatched by /claudit during Phase 2.
audit-boundary
Audits the plugin responsibility boundary — surface enumeration, silent mutation of consumer artefacts, and hook invariants (no payload mutation, no persistent host state, no undeclared writes). Dispatched by /hone Phase 2 against every plugin.
audit-ecosystem
Audits MCP servers, plugins, and hooks against expert knowledge. Dispatched by /claudit during Phase 2.
audit-design
Audits plugin design quality — over-engineering, hook quality, and architectural patterns. Dispatched by /hone during Phase 2.
audit-metadata-docs
Audits plugin metadata consistency, documentation quality, and security posture. Dispatched by /hone during Phase 2.
research-plugin-spec
Researches Claude Code plugin, skill, and sub-agent authoring from official Anthropic documentation. Shared by /smith and /hone.