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/mworldorg/markdown-memory/mm-focusnpx skills add mworldorg/markdown-memory --skill mm-focusgit clone --depth 1 https://github.com/mworldorg/markdown-memoryWhat 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 | $0.00129 | $0.00810 |
| Opus 5 | $0.00064 | $0.00405 |
| Sonnet 5 | $0.00026 | $0.00162 |
| Haiku 4.5 | $0.00013 | $0.00081 |
Grade A, and why
mm-focus 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mm-focus — СНЯТ 2026-08-02
Скилл ничего не загружает. Если его вызвали — объясни замену и остановись.
Почему снят
Детекция текущего этапа дублировала /gsd-resume-work и при этом расходилась с фактической раскладкой GSD Core:
- искал литеральные
PLAN.md/CONTEXT.md/SUMMARY.md, тогда как файлы лежат с префиксом фазы —61-CONTEXT.md,61-01-PLAN.md,61-01-SUMMARY.md(а в одной фазе встречается и57-PLAN.mdбез индекса плана); - считал фазу однопланной, тогда как фаза бывает multi-plan — 6 планов в 61-й, 7 в 67-й;
- брал текущую фазу из
current_phaseвSTATE.md, а тот указывал на закрытую фазу 66, когда живая работа шла в 61; в другом проекте ключаcurrent_phaseнет вообще.
Итог: этап определялся неверно, в контекст грузились не те файлы, и скилл об этом молчал.
Чинить не стали: /gsd-resume-work делает ту же детекцию правильно — обходит планы глобом *-PLAN.md с парным SUMMARY (обе формы имён), читает HANDOFF.json и .continue-here*.md, знает про async-job манифесты. Держать свой детектор чужой раскладки — то же самое, обо что скилл и сломался.
Что делать вместо
Сориентироваться после /clear в GSD-проекте:
/gsd-resume-work
Определит фазу и предложит меню действий.
Если нужна именно молчаливая загрузка файлов этапа — без меню и предложений, ради чего этот скилл и заводился, — попроси прямо, одной репликой:
Прочитай целиком .planning/phases/61-source-rotation-position-mode-visibility/61-CONTEXT.md
и открытые планы этой фазы: 61-04-PLAN.md, 61-05-PLAN.md, 61-06-PLAN.md.
Ничего не пересказывай и не предлагай — просто загрузи в контекст и жди.
Каталог фазы и текущий план бери из .planning/HANDOFF.json — поля phase_dir и plan. Это единственный признак, который на проверке дал верный ответ и в проекте с живой фазой, и в проекте между фазами; current_phase из STATE.md для этого непригоден.
В не-GSD проекте — /mm resume.
Перед /clear
Снятие скилла не отменяет гейта: перед чисткой контекста — /mm gate и его вердикт из exit code.
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 · 48 lines · 129 tokens per session scan A 153b70599133
mm-focus is a skill published in the GitHub repository mworldorg/markdown-memory (25 stars, last pushed 16d ago), licensed MIT. It adds 129 tokens to every session and 810 once invoked, about $0.0006 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
constraint-driven-development
Establishes a project's quality bar as a written contract and stops agents quietly lowering it. Interviews the user on which dimensions matter, supplies sane default thresholds when they have no number in mind, records everything in CONSTRAINTS.md, and watches the diff for a weakened bar — new @ts-ignore or…
git-workflow-and-versioning
Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, opening or reviewing a pull request (PR), pushing to a remote, or when you need to organize work across multiple parallel streams. Use when cutting a release, choosing a semantic version bump…
test-driven-development
Drives development with tests. Use when implementing any logic, fixing any bug, or changing any behavior. Use when you need to prove that code works, when a bug report arrives, or when you're about to modify existing functionality.
documentation-and-adrs
Records decisions and documentation. Use when making architectural decisions, changing public APIs, shipping features, or when you need to record context that future engineers and agents will need to understand the codebase.
shipping-and-launch
Prepares production launches. Use when preparing to deploy to production. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.
spec-driven-development
Creates specs before coding. Use when starting a new project, feature, or significant change and no specification exists yet. Use when requirements are unclear, ambiguous, or only exist as a vague idea. Use when a single requirement spans several independently testable capabilities and needs decomposing into a…