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 skills add synaptiai/agent-capability-standard --skill discover-capabilitiesgit 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/discover-capabilities)<a href="https://agentmods.dev/skills/synaptiai/agent-capability-standard/discover-capabilities"><img src="https://agentmods.dev/badge/skills/synaptiai/agent-capability-standard/discover-capabilities.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 | $0.00050 | $0.01803 |
| Opus 5 | $0.00025 | $0.00901 |
| Sonnet 5 | $0.00010 | $0.00361 |
| Haiku 4.5 | $0.00005 | $0.00180 |
Grade A, and why
discover-capabilities 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 8d 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 — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Intent
Execute discover-capabilities to analyze a natural language task description and automatically:
- Detect which ontology capabilities are needed
- Identify gaps where the ontology lacks coverage
- Synthesize a valid workflow DAG from matched capabilities
This skill bridges the gap between "I want to do X" and "here are the specific capabilities and workflow steps needed to do X safely."
Success criteria:
- All atomic actions in the task are identified
- Each action maps to an ontology capability with confidence score
- Missing capabilities are flagged with proposed extensions
- A valid workflow is synthesized with proper safety steps
- Evidence anchors trace the discovery reasoning
Compatible schemas:
schemas/capability_ontology.yamlschemas/workflow_catalog.yaml
Inputs
| Parameter | Required | Type | Description |
|---|---|---|---|
task_description |
Yes | string | Natural language description of the task to analyze |
domain |
No | string | Domain context for specialization (e.g., "security", "data-pipeline") |
Procedure
-
Load ontology context: Read the capability ontology to understand available capabilities
- Load
schemas/capability_ontology.yamlvia CapabilityRegistry - Load
schemas/workflow_catalog.yamlvia WorkflowEngine - Note: 36 atomic capabilities across 9 cognitive layers
- Load
-
Analyze task: Decompose the task into atomic capability requirements
- Parse the task description for action verbs and targets
- Map each action to the closest ontology capability
- Assign confidence scores based on semantic match quality
- Identify domain parameters where applicable
-
Classify matches: Validate and filter capability matches
- Accept matches with confidence >= 0.6
- Route low-confidence matches to gap detection
- Identify unmatched requirements
-
Detect gaps: For unmatched requirements
- Find nearest existing capabilities by semantic similarity
- If available, generate proposed new capabilities with:
- Suggested layer, risk level, and schemas
- Edges to related existing capabilities
- Rationale for the proposal
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.
- 8d ago First seen · 246 lines · 50 tokens per session scan A ac4dada49106
discover-capabilities is a skill published in the GitHub repository synaptiai/agent-capability-standard (4 stars, last pushed 8d ago), licensed Apache-2.0. It adds 50 tokens to every session and 1,803 once invoked, about $0.0003 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
A set of Korean-language conversation and safety instructions for people new to coding and AI. It tells the assistant to explain difficult terms and guide the user with one clear next action.
sodam-harness-self-check
A self-checking instruction set for an AI agent. It tells the agent to verify important work, show evidence, and clearly disclose anything it could not check.
sodam-harness-beginner-tone
A short note saying this add-on has been merged into another beginner-focused writing guide.