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/plannpx skills add synaptiai/agent-capability-standard --skill plangit 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/plan)<a href="https://agentmods.dev/skills/synaptiai/agent-capability-standard/plan"><img src="https://agentmods.dev/badge/skills/synaptiai/agent-capability-standard/plan.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 | $0.00037 | $0.02790 |
| Opus 5 | $0.00018 | $0.01395 |
| Sonnet 5 | $0.00007 | $0.00558 |
| Haiku 4.5 | $0.00004 | $0.00279 |
Grade C, and why
plan scanned grade C 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 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.
Instruction-override phrasinghighPrompt injection
Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.
- Never generate plans that bypass safety constraints How it starts
The opening of the file, as written. The whole thing — 336 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Intent
Create a structured, executable plan that decomposes a goal into ordered steps with clear dependencies, verification criteria for each step, checkpoint placement for safety, and rollback strategies for recovery.
This capability is the GATEWAY to all actions. No mutating operation should proceed without a validated plan.
Success criteria:
- Goal is decomposed into atomic, verifiable steps
- Dependencies form a valid DAG (no cycles)
- Each mutating step has rollback strategy defined
- Checkpoints placed before high-risk operations
- Estimated risk level accurately reflects plan complexity
Compatible schemas:
schemas/output_schema.yaml
Inputs
| Parameter | Required | Type | Description |
|---|---|---|---|
goal |
Yes | string | Clear statement of what the plan should achieve |
context |
No | object | Current state, available resources, constraints |
constraints |
No | object | Time limits, resource bounds, policy restrictions |
risk_tolerance |
No | string | low, medium, high - affects checkpoint frequency |
max_steps |
No | integer | Maximum number of steps to generate |
Procedure
-
Understand the goal: Parse and clarify the objective
- Identify success criteria explicitly
- Detect ambiguity and resolve or flag it
- Determine scope boundaries
-
Analyze context: Gather relevant information
- Read minimal files needed to understand current state
- Identify existing patterns and conventions
- Note constraints from environment or policy
-
Decompose into steps: Break goal into atomic operations
- Each step should be independently verifiable
- Prefer small, reversible changes
- Order by logical dependencies
- Use
decomposecapability patterns
-
Define dependencies: Map step relationships
- Create DAG of step dependencies
- Identify parallel-safe steps
- Flag blocking dependencies
-
Add verification criteria: Specify how to check each step
- Define concrete, testable conditions
- Include expected outputs or state changes
- Reference files or commands for verification
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 · 336 lines · 37 tokens per session scan C 2ced876874b6
plan is a skill published in the GitHub repository synaptiai/agent-capability-standard (4 stars, last pushed 5d ago), licensed Apache-2.0. It adds 37 tokens to every session and 2,790 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (instruction-override phrasing). 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.