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 mworldorg/markdown-memory --skill mm-clear-gategit clone --depth 1 https://github.com/mworldorg/markdown-memoryWrote 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/mworldorg/markdown-memory/mm-clear-gate)<a href="https://agentmods.dev/skills/mworldorg/markdown-memory/mm-clear-gate"><img src="https://agentmods.dev/badge/skills/mworldorg/markdown-memory/mm-clear-gate/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/mworldorg/markdown-memory/mm-clear-gate"><img src="https://agentmods.dev/badge/skills/mworldorg/markdown-memory/mm-clear-gate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
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 | $0.00167 | $0.02145 |
| Opus 5.5 | $0.00067 | $0.00858 |
| Sonnet 5.5 | $0.00033 | $0.00429 |
| Haiku 4.5 | $0.00017 | $0.00215 |
Grade A, and why
mm-clear-gate 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 1mo 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mm-clear-gate — гейт перед /clear
Решает проблему: единственным подтверждением «всё сохранено» была фраза модели о сессии, память о которой /clear и стирает. Вердикт должен приходить из скрипта с exit code, а не из реплики.
Вся логика — в скрипте. Скилл его запускает, печатает вывод целиком и переводит exit code в одну строку. Ничего не пересчитывает и не пересказывает.
Запуск
python <repo>/scripts/clear-gate.py --mode mid # дефолт: между этапами GSD
python <repo>/scripts/clear-gate.py --mode end # конец сессии
<repo> — корень mm-репозитория (paths.skills_repo из конфига). Проверяемый проект — текущий cwd; можно задать явно через --project <путь>.
Режим: /mm gate → mid, /mm gate end (или «конец сессии», «закругляемся») → end.
Что делать с выводом
- Напечатай вывод скрипта целиком, дословно — секции блокеров, предупреждений и пройденного. Не сокращай список файлов, не убирай подсказки-команды.
- Добавь одну строку по exit code:
0→✅ Гейт пройден — можно /clear.1→⛔ Гейт не пройден — чистить нельзя, сначала закрой блокеры выше.
- При exit 1 не предлагай
/clearи не утверждай, что всё записано. Блокеры перечислены — назови их и остановись. - Ничего не чини сам. Гейт read-only, исправления — отдельное решение оператора.
Планка по режимам
| Проверка | mid | end |
|---|---|---|
Свежесть GSD-handoff в репозитории проекта (.planning/HANDOFF.json, .continue-here.md) |
блокер | блокер |
Свежесть vault-файлов для Project Knowledge (handoff.md, dashboard.md) |
предупреждение³ | блокер³ |
| Vault-репо: грязный или не запушен | блокер | блокер |
| Дерево проекта незакоммичено | предупреждение¹ | блокер |
| HEAD впереди origin | предупреждение | блокер |
Лог сессии в <vault>/sessions/ |
не проверяется | блокер |
Фаза Complete без passing-VERIFICATION.md |
блокер² | блокер² |
validate.health |
предупреждение | предупреждение |
¹ становится блокером, если GSD-handoff устарел: незаписанное состояние плюс грязное дерево — это уже потеря.
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.
- 1mo ago First seen · 74 lines · 167 tokens per session scan A dd14401c820e
mm-clear-gate is a skill published in the GitHub repository mworldorg/markdown-memory (25 stars, last pushed 4d ago), licensed MIT. It adds 167 tokens to every session and 2,145 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
agent-memory-mcp
A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).
agent-memory-discipline
Rules for when an agent should recall from long-term memory before acting and when it should save decisions, corrections and failures afterwards. Works with any memory backend.
agent-memory
A hybrid memory system that provides persistent, searchable knowledge management for AI agents.
accint-frames
Drain acc's deliberation queue — open/waiting brainframes checkpointed by headless runs — via accact(runtime="continue").
accint-solve
Route a goal through acc's scored-memory loop via accact(runtime="solve"); deliberate any returned brainframe and submit via continue.
agent-memory-systems
Memory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: short-term (context window), long-term (vector stores), and the cognitive architectures that organize them.