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/comparenpx skills add synaptiai/agent-capability-standard --skill comparegit 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/compare)<a href="https://agentmods.dev/skills/synaptiai/agent-capability-standard/compare"><img src="https://agentmods.dev/badge/skills/synaptiai/agent-capability-standard/compare.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 | $0.00030 | $0.03006 |
| Opus 5 | $0.00015 | $0.01503 |
| Sonnet 5 | $0.00006 | $0.00601 |
| Haiku 4.5 | $0.00003 | $0.00301 |
Grade A, and why
compare 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 4d 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 — 387 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Intent
Systematically evaluate multiple alternatives against defined criteria to produce a recommendation with transparent tradeoff analysis. Comparison enables informed decision-making through structured analysis.
Success criteria:
- All options evaluated against same criteria
- Criteria weighted by importance
- Clear recommendation with rationale
- Tradeoffs explicitly documented
Compatible schemas:
schemas/output_schema.yaml
Inputs
| Parameter | Required | Type | Description |
|---|---|---|---|
options |
Yes | array[string|object] | Alternatives to compare (2+ items) |
criteria |
Yes | array[string|object] | Evaluation dimensions with optional weights |
context |
No | object | Constraints, priorities, or decision context |
must_have |
No | array[string] | Required criteria (eliminates options that fail) |
Procedure
-
Enumerate options: List all alternatives under consideration
- Verify each option is viable (not obviously invalid)
- Ensure options are at same abstraction level
- Flag if options are not mutually exclusive
-
Define criteria: Establish evaluation dimensions
- Quantitative criteria: measurable (cost, time, size)
- Qualitative criteria: assessed (quality, maintainability, risk)
- Apply must_have filters to eliminate non-viable options
-
Assign weights: Determine relative importance of each criterion
- Weights should sum to 1.0
- If not provided, use equal weights
- Document rationale for weight assignments
-
Score each option: Evaluate options against criteria
- Quantitative: normalize to 0-1 scale
- Qualitative: rate as 0.0 (poor) to 1.0 (excellent)
- Document evidence for each score
-
Calculate weighted scores: Aggregate criteria scores
- weighted_score = sum(criterion_score * criterion_weight)
- Rank options by weighted score
-
Analyze tradeoffs: Document what each choice sacrifices
- Identify criteria where top choice is not best
- Quantify the gap between options on key criteria
What ships with it
2 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.
- 4d ago First seen · 387 lines · 30 tokens per session scan A 12e385585b2f
compare is a skill published in the GitHub repository synaptiai/agent-capability-standard (4 stars, last pushed 4d ago), licensed Apache-2.0. It adds 30 tokens to every session and 3,006 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.
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.
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.