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/observenpx skills add synaptiai/agent-capability-standard --skill observegit 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/observe)<a href="https://agentmods.dev/skills/synaptiai/agent-capability-standard/observe"><img src="https://agentmods.dev/badge/skills/synaptiai/agent-capability-standard/observe.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 | $0.00035 | $0.01550 |
| Opus 5 | $0.00017 | $0.00775 |
| Sonnet 5 | $0.00007 | $0.00310 |
| Haiku 4.5 | $0.00003 | $0.00155 |
Grade A, and why
observe 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 6d 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 — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Intent
Observe and report the current state of a specified target without modifying it. This is the foundation for situational awareness and state modeling.
Success criteria:
- Current state accurately captured with timestamp
- Relevant aspects of the target documented
- At least one evidence anchor per observation
- Uncertainty explicitly noted where state is ambiguous
Compatible schemas:
schemas/output_schema.yaml
Inputs
| Parameter | Required | Type | Description |
|---|---|---|---|
target |
Yes | string | What to observe (file path, URL, process, system) |
aspects |
No | array[string] | Specific aspects to focus on (e.g., ["status", "errors", "metrics"]) |
depth |
No | string | Observation depth: surface, detailed, exhaustive |
Procedure
-
Identify observation target: Clarify exactly what system, process, or entity to observe
- Validate target is accessible and observable
- Determine appropriate observation method (read file, query API, check process)
-
Select observation aspects: Determine what properties/attributes to capture
- If aspects not specified, observe: status, configuration, recent changes, anomalies
- Prioritize aspects relevant to apparent context or goal
-
Capture current state: Execute observation without modifying target
- Use Read for file-based targets
- Use Bash for process/system state (ps, systemctl status, etc.)
- Record timestamp of observation
-
Document observations: Structure findings with evidence
- Note what was observed and when
- Highlight notable conditions or anomalies
- Record uncertainty where state is unclear
-
Ground claims: Attach evidence anchors to all observations
- Format:
file:linefor file content - Format:
command:outputfor system observations
- Format:
Output Contract
Return a structured object:
observation:
target: string # What was observed
timestamp: string # ISO 8601 timestamp
status: string # Overall status assessment
aspects:
- aspect: string # Name of observed aspect
value: any # Observed value or state
notable: boolean # Whether this is noteworthy
anomalies: array[string] # Unexpected findings
confidence: 0..1 # Based on observation quality
evidence_anchors: ["file:line", "command:output"]
assumptions: [] # What was assumed about the target
next_actions: array[string] # 0-3 suggested follow-ups
What ships with it
5 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.
- 6d ago First seen · 206 lines · 35 tokens per session scan A 01755fda5605
observe is a skill published in the GitHub repository synaptiai/agent-capability-standard (4 stars, last pushed 7d ago), licensed Apache-2.0. It adds 35 tokens to every session and 1,550 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
gh
GitHub API access and project management automation for the hallucination-detector repo. Uses octokit with proxy-aware client for all GitHub operations — issues, PRs, labels, milestones, Projects V2. No gh CLI required.
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.