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/cwinvestments/memstack/goalnpx skills add cwinvestments/memstack --skill goalgit clone --depth 1 https://github.com/cwinvestments/memstackWhat 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 | $0.00058 | $0.01503 |
| Opus 5 | $0.00029 | $0.00751 |
| Sonnet 5 | $0.00012 | $0.00301 |
| Haiku 4.5 | $0.00006 | $0.00150 |
Grade A, and why
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 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🎯 Goal — Finish Line Defined
Define what "done" looks like and how you'll prove it — before you write a line of code.
Activation
When this skill activates, output:
🎯 Goal — Finish line defined.
Then walk the user through the five fields in order, one prompt at a time or as a single template — whichever fits the flow. Fill in what the request already tells you; ask only for what's missing. Put the most weight on VERIFICATION: it is the field that is required, the field that is skipped most often, and the field that turns "I think it's done" into "I can show it's done." Do not let a goal close without a concrete, checkable verification criterion.
Context Guard
| Context | Status |
|---|---|
| User says "goal", "set a goal", "define the goal", "plan this properly" | ACTIVE — structure the five fields |
| User is starting a non-trivial task with a fuzzy finish line | ACTIVE — offer to define the goal first |
| User asks "how will we know this is done?" / "what's the definition of done?" | ACTIVE — VERIFICATION-first |
| User is mid-execution and just wants the next step | DORMANT — use work, not goal |
| The goal is already clearly stated with a checkable outcome | DORMANT — don't re-litigate a good goal |
| Casual question, chit-chat, or a one-line lookup | DORMANT — do not activate |
The Five Fields
A goal is a task with a finish line you can stand on. Five fields:
- TASK — what to do. The concrete action, in one sentence. Required.
- WHY — why it matters / who it's for. Optional, but it keeps scope honest and kills gold-plating. Skip it if it's obvious.
- OUTCOME — the exact finished result — the definition of done. Not "improve X" but the specific end state that exists when you're finished. Required.
- CONSTRAINTS — what must or must not be done. Boundaries: no new dependencies, don't change the public API, stay under budget. Optional; list as many as apply.
- VERIFICATION — how you'll PROVE the outcome is complete. A concrete, observable, checkable criterion — a command to run, an output to see, a behavior to reproduce. Required, and load-bearing.
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 · 111 lines · 58 tokens per session scan A 1a8a48ec019d
goal is a skill published in the GitHub repository cwinvestments/memstack (417 stars, last pushed 5d ago), licensed MIT. It adds 58 tokens to every session and 1,503 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 2026-08-30.
Other skills, from other repositories
plan-ceo-review
CEO/founder-mode plan review. Rethink the problem, find the 10-star product, challenge premises, expand scope when it creates a better product. Four modes: SCOPE EXPANSION (dream big), SELECTIVE EXPANSION (hold scope + cherry-pick expansions), HOLD SCOPE (maximum rigor), SCOPE REDUCTION (strip to essentials). Use when…
ship
Ship workflow: detect + merge base branch, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, and create a PR. Use for an explicit /ship invocation or when the user requests the full ship, release, or deploy workflow. For an ordinary commit, push, or pull-request publishing request, use the built-in…
design-review
Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them. Iteratively fixes issues in source code, committing each fix atomically and re-verifying with before/after screenshots. For plan-mode design review (before implementation), use…
plan-eng-review
Eng manager-mode plan review. Lock in the execution plan — architecture, data flow, diagrams, edge cases, test coverage, performance. Walks through issues interactively with opinionated recommendations. Use when asked to "review the architecture", "engineering review", or "lock in the plan". Proactively suggest when…
pre-landing-review
Pre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust boundary violations, conditional side effects, and other structural issues. Use when explicitly asked for the specialized pre-landing workflow. Product /review requests are handled by BitFun's unified Review mechanism instead.…
autoplan
Auto-review pipeline — reads the full CEO, design, eng, and DX review skills from disk and runs them sequentially with auto-decisions using 6 decision principles. Surfaces taste decisions (close approaches, borderline scope, codex disagreements) at a final approval gate. One command, fully reviewed plan out. Use when…