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 MichelKerkmeester/skilled-agent-harness_spec-driven-loops --skill sk-create-goalgit clone --depth 1 https://github.com/MichelKerkmeester/skilled-agent-harness_spec-driven-loopsWrote 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/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-create-goal)<a href="https://agentmods.dev/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-create-goal"><img src="https://agentmods.dev/badge/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-create-goal/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-create-goal"><img src="https://agentmods.dev/badge/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-create-goal.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00025 | $0.03281 |
| Opus 5.5 | $0.00010 | $0.01312 |
| Sonnet 5.5 | $0.00005 | $0.00656 |
| Haiku 4.5 | $0.00003 | $0.00328 |
Grade A, and why
sk-create-goal 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 today.
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- sk-create-goal — 86% identical, 43 lines differ
How it starts
The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Canonical source:
.skilled/skills/sk-doc/sk-create-goal/. This is a generated markdown-only copy so Hermes can load the skill without scanning the canonical directory. Readreferences/,assets/andscripts/from the canonical path above.
Create Packet Goals
sk-create-goal authors goal.md content for an existing spec packet. It fills per-kind templates that are checked copies of the system-spec-kit goal template and keeps runtime goal state with its existing owners.
1. WHEN TO USE
Activation Triggers
Use this packet to:
- Author or revise a top-level goal or phase-parent goal.
- Author or revise a nested phase-child goal.
- Add
goal.mdto an existing packet that has no goal. - Add a binding row and matching child goal when someone adds a phase.
- Cut an over-budget parent goal without dropping a completion criterion.
- Print a parent goal's chat slice for the operator to set or resend.
- Handle a request that enters through
/create:goal.
Keyword triggers: create packet goal, author goal.md, revise packet goal, phase parent goal, nested phase child goal, add a goal file, goal chat slice, /create:goal.
When NOT to Use
- The target packet does not exist. Use system-spec-kit to create it first.
- The packet's phase structure is not established. Use system-spec-kit to plan the phases first.
- The request is to set, bind, inject or resend a session objective. Redirect it to the goal hooks or the host's native goal command.
- The request changes runtime goal behavior or system-spec-kit template tooling. Those owners remain outside this packet.
This packet authors files only. Its goal-file work does not change session state.
2. SMART ROUTING
Run these four decisions before writing:
- File content or session state? A request to author or revise a packet's
goal.mdis file work. A request to set, bind, inject or resend a session objective belongs to the goal hooks or the host's native goal command. Redirect session-state requests without editing a packet goal. - Does the packet exist? What role does it have? Confirm the target directory exists. A nested phase child has a parent directory containing
spec.md. A packet with direct phase-child directories is the phase parent. Otherwise, treat it as a top-level packet. If the packet is missing, route packet creation to system-spec-kit first. - Does
goal.mdexist? Revise an existing goal. Add one to an existing packet that has none. Do not treat a missing packet as a goal-file request. - Does a child change alter a parent decision or criterion? If it does, amend the parent first. Then print the updated parent chat slice for the operator to resend. Do not let a child goal override a parent decision.
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.
- today Changed bd9b999f7bb1
- 5d ago Changed 53ac343cb3ca
- 14d ago Changed 908a1a340423
- 16d ago Changed a82edfd0251b
- 19d ago Changed ee0b1c248147
- 20d ago First seen · 189 lines · 25 tokens per session scan A f507855f9b7e
sk-create-goal is a skill published in the GitHub repository MichelKerkmeester/skilled-agent-harness_spec-driven-loops (37 stars, last pushed yesterday), licensed MIT. It adds 25 tokens to every session and 3,281 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-27.
Other skills, from other repositories
story-readiness
Is a story implementation-ready? Checks clear acceptance criteria, open questions, ADR refs. READY/NEEDS WORK/BLOCKED/NOT ASSESSED.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.
handle-linkedin-connection-request-signal
Use this skill when someone sends a team member an inbound LinkedIn connection request. An inbound request is a deliberate, ACTIVE first-party intent signal — meaningfully stronger than a passive profile view — and it deserves different scoring rules. The skill resolves and enriches the requester, gates them through…