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/choiyounggi/groundwork/remembernpx skills add choiyounggi/groundwork --skill remembergit clone --depth 1 https://github.com/choiyounggi/groundworkWhat 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 | $0.00051 | $0.00650 |
| Opus 5 | $0.00026 | $0.00325 |
| Sonnet 5 | $0.00010 | $0.00130 |
| Haiku 4.5 | $0.00005 | $0.00065 |
Grade A, and why
remember 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 2d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
memory-loop: remember
A wrongly saved memory gets recalled later as if it were fact — that is one of the biggest sources of persistent hallucination. This gate blocks it at the entrance.
The gate (in order, before any write)
-
State the candidate and its evidence. What exactly would be saved, and how was it verified? An unverified inference is never saved — verify it first or drop it.
-
Confirm the tier with the user:
tier: long— keeps applying indefinitely (identity, policies, infrastructure facts, recurring preferences).tier: short— consumed by a date or an event (schedules, in-flight work, decisions pending).
-
If short, agree on the expiry:
- Absolute:
expires: YYYY-MM-DD. The expiry sweep archives it on the first session after that date has passed — the expiry day itself is still live (exclusive boundary). - Conditional:
expires_when: "<event>"(e.g. "after the release ships"). Never auto-archived; you review it manually when the event happens.
- Absolute:
-
Write the memory file in the native format — the usual frontmatter (
name,description,metadata) — adding the lifecycle keys undermetadata:--- name: deploy-freeze-january description: Deploys are frozen until the audit completes metadata: type: project tier: short expires: 2026-02-01 --- <the fact> -
Update the memory index (
MEMORY.mdin the same directory) with a one-line pointer.
Optional: salience: 1-5 (recall priority) may be added under metadata;
memory-loop does not enforce it — it is a hint for your own recall ordering.
Compatibility contract
Files without a tier key are outside the lifecycle — the sweep never
touches them. That is the safe default for every memory that existed before
this plugin was installed. Never bulk-add tier to old files; tier them one
by one, through this gate, as they come up.
When the sweep reports
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.
- 2d ago First seen · 67 lines · 51 tokens per session scan A ec1215bc34ee
remember is a skill published in the GitHub repository choiyounggi/groundwork (3 stars, last pushed 2d ago), licensed MIT. It adds 51 tokens to every session and 650 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
dummy-dataset
Generate realistic dummy datasets for testing with customizable columns, constraints, and output formats (CSV, JSON, SQL, Python script). Use when creating test data, building mock datasets, or generating sample data for development and demos.
outcome-roadmap
Transform an output-focused roadmap into an outcome-focused one that communicates strategic intent. Rewrites initiatives as outcome statements reflecting user and business impacts. Use when shifting to outcome roadmaps, making a roadmap more strategic, or rewriting feature lists as outcomes.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
retro
Facilitate a structured sprint retrospective — what went well, what didn't, and prioritized action items with owners and deadlines. Use when running a retrospective, reflecting on a sprint, creating action items from team feedback, or learning how to run effective retros.
shipping-artifacts
The durable documentation set that makes an AI-built (vibe-coded) app reviewable before shipping. A small core every app needs — architecture, user/permission flows, permissions, variables/secrets, and a test-coverage map — plus conditional docs added only when they apply: emails, scheduled work, SEO, and embedded…
ideal-customer-profile
Identify the Ideal Customer Profile (ICP) from research data with demographics, behaviors, JTBD, and needs. Use when defining your ICP, analyzing PMF survey data, or understanding who your best customers are.