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 commands/missingpackage/nightshift/goal-briefgit clone --depth 1 https://github.com/MissingPackage/nightshiftWhat 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 | $0.00020 | $0.00370 |
| Opus 5 | $0.00010 | $0.00185 |
| Sonnet 5 | $0.00004 | $0.00074 |
| Haiku 4.5 | $0.00002 | $0.00037 |
Grade A, and why
goal-brief 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 yesterday.
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.
What it actually says
Take my raw goal below and draft the structured goal contract I will feed to /goal. Do NOT start executing the goal — the deliverable of this command is the contract text, printed for my review.
Draft it in exactly this shape, filling gaps with your best inference from the repo state and flagging every inference with [ASSUMED] so I can correct it:
GOAL: <one sentence, outcome not activity>
DONE WHEN (all measurable):
- <condition 1 — verifiable by a command/artifact, not by judgment>
- <condition 2>
EVIDENCE OF DONE: <exact commands/artifacts that will prove each condition>
AUTHORITY GRANTED:
- may do autonomously: <e.g. create branches, open PRs, run tests, spend up to €X>
- must docket (never do): <e.g. merge to dev, touch deploy repo, change public APIs, delete >30-day-old code>
CONSTRAINTS: <standing rules that apply — attribution, protected paths, budget, conventions>
WORKING PROTOCOL: follow skills loop-iteration + done; verifier gate per cycle; digest every cycle; stop-by-design when the remaining work is docket-gated.
CONTEXT ANCHORS: <files to read first: HANDOFF.md, tracker query, specs>
Rules for the draft: split heterogeneous objectives into separate goals (a goal with "and also…" chains loses its completion condition); reject any DONE-WHEN that a verifier could not check mechanically — rewrite it until it is checkable; keep AUTHORITY explicit even when it feels obvious — implied authority is how unwanted merges happen.
Raw goal: $ARGUMENTS
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.
- yesterday First seen · 32 lines · 20 tokens per session scan A 516715a918d2
goal-brief is a command published in the GitHub repository MissingPackage/nightshift (2 stars, last pushed 16d ago), licensed MIT. It adds 20 tokens to every session and 370 once invoked, about $0.0001 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 commands, from other repositories
research
Research a technical or product question.
safe-build
Build the application for development or production.
update
Use when: search results seem noisy, after bulk imports, or for periodic memory/registry maintenance.
plan-workflow
Generate a skill chain plan for a high-level goal by analyzing the skills registry for input/output compatibility.
music-suno-prompt
Grounded Suno prompt synthesis from local knowledge corpus + persona canon + label canon. No vibes-prompting.
lrn
Execute the /vibeguard:learn command. $ARGUMENTS.