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/daaaaave/agentic-workspace-core/project-knowledgenpx skills add Daaaaave/agentic-workspace-core --skill project-knowledgegit clone --depth 1 https://github.com/Daaaaave/agentic-workspace-coreWhat 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 | $0.00074 | $0.03036 |
| Opus 5 | $0.00037 | $0.01518 |
| Sonnet 5 | $0.00015 | $0.00607 |
| Haiku 4.5 | $0.00007 | $0.00304 |
Grade A, and why
project-knowledge 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 — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Knowledge
Goal
Operate repository knowledge as a small, inspectable, reviewable memory system. Recall relevant durable knowledge before it can affect work, update the canonical owner when durable facts change, and keep temporary state out of project memory.
The policy authority for memory behavior is .agents/knowledge-core/memory-policy.md. This skill is the operating procedure for applying that policy.
Use When
- The user asks to inspect, update, create, clean, validate, or reason about project knowledge, memory, docs, decisions, runbooks, plans, glossary, domain terms, workflows, or project context.
- Before non-trivial work that may depend on project history: architecture, database, auth, deployment, testing, domain behavior, conventions, migrations, infrastructure, shared APIs, or previous decisions.
- Before making or changing a decision future agents will need to follow.
- When docs, code, generated indexes, user statements, or previous decisions conflict.
- When an error, failed check, or user correction may already have a project-specific explanation.
- After a non-obvious bug fix, failed approach, user correction, production issue, migration, workflow change, or repeated gotcha that future agents should not rediscover.
- When deciding whether information belongs in
docs/,.agents/skills/,.context/handoffs/,legacy/, or outside the repository. - When authored docs changed and generated indexes or validation may be stale.
Do Not Use When
- The task is a tiny local edit with no dependency on project conventions or durable knowledge.
- The user asks for external/current research; use
research-to-knowledgeunless the only task is routing the result into existing docs. - The user asks to create or revise a procedural skill; use
write-agent-skill. - The user asks for temporary transfer state; use
write-agent-handoff. - The content is private, personal, credential-like, or not meant to be shared with project contributors.
- A deterministic script fully answers the task; run it instead of narrating around it.
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 · 257 lines · 74 tokens per session scan A 48210c45b9b3
project-knowledge is a skill published in the GitHub repository Daaaaave/agentic-workspace-core (6 stars, last pushed 2mo ago), licensed MIT. It adds 74 tokens to every session and 3,036 once invoked, about $0.0004 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
evolve
Use when many related hardened instincts (high-confidence feedback/discovery memories) have piled up in one domain, when the user runs /evolve or asks to promote, cluster, graduate, or consolidate accumulated instincts into a Command, Skill, or Agent, or when files in Instinct Proposals need review. Part of the…
memex-retro
Save insights from completed tasks to Zettelkasten memory.
capture-knowledge
将对话、项目文档、调试经验或用户指定材料沉淀到 Second Brain。用于“保存知识”“提取经验”“导入文档”“记录到知识库”“capture knowledge”等请求；先保存可追溯来源，再按一个稳定主题一张卡提取或更新 canonical 页面，禁止把 README、报告、故事或整段会话直接做成一张大卡。.
second-brain-learn
从当前 Agent 对话和工作轨迹中挖掘可长期保留的偏好、方法、Agent 角色事实、项目规则、知识与山脉进展；审计现有 owner，新增、纠错、缩限、替代、合并、迁移或退役规则，自动合并有证据的低风险变化，高风险变更先询问用户，并同步当前 Agent。用户说学习、记住、采纳或停止某种行为、修正规则、保存本次经验、从当前对话改进、运行 /learn，或要求未来 Agent 遵守某项教训时使用。.
epiphany
Roam the Ultan memory library and surface ONE non-obvious, useful connection between distant entries — an on-demand "epiphany". Use when the user asks for a spark/insight/epiphany from their memory, wants a hidden cross-cutting pattern surfaced, asks "show me something interesting in my notes", or runs /epiphany. Can…
ultan-search
Search and traverse the user's Ultan memory library (/.agent-mem/knowledge/). Use whenever you see an Ultan wikilink in priming context (e.g. [[projects/foo/bar]]) and want to read it, OR when you want to find entries by topic. Accepts a wikilink/path (returns the entry plus directory context — siblings, subfolders…