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/synaptiai/agent-capability-standard/receivenpx skills add synaptiai/agent-capability-standard --skill receivegit clone --depth 1 https://github.com/synaptiai/agent-capability-standardWrote 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/synaptiai/agent-capability-standard/receive)<a href="https://agentmods.dev/skills/synaptiai/agent-capability-standard/receive"><img src="https://agentmods.dev/badge/skills/synaptiai/agent-capability-standard/receive.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 5.1 | $0.00038 | $0.02664 |
| Opus 5 | $0.00019 | $0.01332 |
| Sonnet 5 | $0.00008 | $0.00533 |
| Haiku 4.5 | $0.00004 | $0.00266 |
Grade B, and why
receive scanned grade B 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 5d 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
- Do not execute or run arbitrary code from received data How it starts
The opening of the file, as written. The whole thing — 358 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Intent
Execute receive to ingest incoming data from external sources and parse it into a structured, validated form for downstream processing.
Success criteria:
- Input data is successfully ingested from the source
- Data is parsed according to expected format
- Validation against schema (if provided) passes or errors are captured
- Structured output is ready for downstream capabilities
- Malformed or unexpected data is handled gracefully
Compatible schemas:
schemas/output_schema.yamlreference/event_schema.yaml
Inputs
| Parameter | Required | Type | Description |
|---|---|---|---|
input_source |
Yes | string|object | Source of incoming data: file path, URL, inline data, or stream identifier |
expected_format |
No | enum | Expected data format: json, xml, yaml, text, csv, binary. Default: auto-detect |
validation_schema |
No | string | Schema to validate parsed data against |
encoding |
No | string | Character encoding. Default: utf-8 |
max_size |
No | string | Maximum input size to accept (e.g., "10MB"). Default: "100MB" |
Procedure
-
Identify input source: Determine where data is coming from
- File path: Read from local filesystem
- URL: Fetch from network endpoint
- Inline: Extract from request payload
- Stream: Connect to data stream
-
Validate source accessibility: Verify source can be read
- Check file exists and is readable
- Verify URL is reachable
- Confirm stream is connected
- Check size does not exceed max_size
-
Detect format: Identify data format if not specified
- Check content-type headers or file extension
- Inspect data prefix for format signatures
- Fall back to text if ambiguous
-
Parse input: Transform raw data into structured form
- JSON: Parse to object/array using safe parser
- XML: Parse to DOM or object representation
- YAML: Parse to object using safe loader
- CSV: Parse to array of records
- Text: Split into lines/tokens as appropriate
- Binary: Extract structured fields per schema
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.
- 5d ago First seen · 358 lines · 38 tokens per session scan B d6da10b03bb4
receive is a skill published in the GitHub repository synaptiai/agent-capability-standard (4 stars, last pushed 6d ago), licensed Apache-2.0. It adds 38 tokens to every session and 2,664 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
evaluate-options
Research and evaluate implementation options before presenting a recommendation. Use when multiple approaches exist for a problem and a decision is needed. Launches one background research agent per option in parallel, collects evidence-backed findings, then presents a recommendation grounded in observed data — not…
delegate
Quick delegation template for sub-agent prompts. Use when assigning work to a sub-agent, before invoking the Task tool, or when preparing prompts for specialized agents. Provides the WHERE-WHAT-WHY framework. For comprehensive delegation guidance, activate the agent-orchestration how-to-delegate skill.
beginner-tone
코딩도 AI도 처음인 초보자와 대화할 때 쓰는 말투·안전 지침. SoDamHarness 설치 시 자동 활성화.
sodam-harness-self-check
작업을 끝내거나 "다 됐어요"라고 말하기 전에 실제로 작동하는지 점검하고 증거를 보여줄 때 사용. 위험·중요 작업 마무리, 완료 선언, 검증 요청 시 적용.
sodam-harness-beginner-tone
이 스킬은 skills/beginner-tone/SKILL.md 로 통합됐습니다.
ai-safe-driver
Use when the agent keeps repeating a mistake, ignores a correction, retries a failed tool unchanged, breaks an output format again, drifts from the latest request, or makes excuses instead of diagnosing recurrence. Also use for a conversation health check, compaction decision, or new-session question.