Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/learnwy/skillsnpx agentmods add skills/learnwy/skills/lwy-knowledge-consolidationWrote 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/learnwy/skills/lwy-knowledge-consolidation)<a href="https://agentmods.dev/skills/learnwy/skills/lwy-knowledge-consolidation"><img src="https://agentmods.dev/badge/skills/learnwy/skills/lwy-knowledge-consolidation/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/learnwy/skills/lwy-knowledge-consolidation"><img src="https://agentmods.dev/badge/skills/learnwy/skills/lwy-knowledge-consolidation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00114 | $0.01331 |
| Opus 5 | $0.00057 | $0.00665 |
| Sonnet 5 | $0.00023 | $0.00266 |
| Haiku 4.5 | $0.00011 | $0.00133 |
Grade A, and why
lwy-knowledge-consolidation 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 11d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Consolidation
Project-local fix journal. One conversation → one structured Markdown file in this repo's IDE folder. Stays with the codebase; ships in the repo; future sessions on this project can find it.
Boundary: project-local debugging/config/workflow/lesson notes belong here. Global, reusable knowledge (architectures, design patterns, API integrations, references) belongs in llm-wiki. KC's
promotecommand moves a doc across the seam when it earns its way into the wiki.
When to use
| Trigger | Action |
|---|---|
| User says "save this", "记录下来", "we solved it" | Run cli.cjs save … |
| Stop nudge fired ("looks like you resolved a non-trivial problem") | Offer to save |
| Solved a bug specific to this codebase | --type debug |
| Locked in a non-obvious config / build setting | --type config |
| Established an ops procedure (deploy / rollback) | --type workflow |
| Post-mortem / retrospective takeaway | --type lesson |
Do not use for: cross-project knowledge (→ llm-wiki), reusable skills (→ project-skill-writer), AI rules (→ project-rules-writer), updating a previously saved doc (KC is write-once).
Prerequisites
- Node.js ≥ 18
- Project root contains an IDE marker dir:
.trae/,.claude/,.cursor/, or.windsurf/
The one command you usually want
node scripts/cli.cjs save \
-r <project_root> \
-a <ai_type> \
-t <type> \
-n <kebab-slug> \
--title "Short, specific title" \
--summary "2-3 sentences readers can stop at" \
--details "Body in Markdown." \
--takeaways "First actionable insight\nSecond insight" \
[--background "<one-line problem context>"] \
[--context "<project / version / component>"] \
[--related "<links / files>"]
Returns the absolute path of the new file. Atomically resolves a date-sequenced name, creates the directory, fills the template, validates required fields.
-a, --ai-type |
trae, trae-cn, claude-code (or claude), cursor, windsurf |
|---|---|
-t, --type |
debug, config, workflow, lesson only — see knowledge-types.md |
-n, --name |
kebab-case slug, ≤50 chars, specific (react-18-hydration-mismatch, not bug-fix) |
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 106 lines · 114 tokens per session scan A c841082ae0da
lwy-knowledge-consolidation is a skill published in the GitHub repository learnwy/skills (4 stars, last pushed 3mo ago), licensed MIT. It adds 114 tokens to every session and 1,331 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 2026-08-31.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.