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 tranfu-labs/tranfu-skills --skill session-to-knowledgegit clone --depth 1 https://github.com/tranfu-labs/tranfu-skillsWrote 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/tranfu-labs/tranfu-skills/session-to-knowledge)<a href="https://agentmods.dev/skills/tranfu-labs/tranfu-skills/session-to-knowledge"><img src="https://agentmods.dev/badge/skills/tranfu-labs/tranfu-skills/session-to-knowledge/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/tranfu-labs/tranfu-skills/session-to-knowledge"><img src="https://agentmods.dev/badge/skills/tranfu-labs/tranfu-skills/session-to-knowledge.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 | $0.00150 | $0.02344 |
| Opus 5 | $0.00075 | $0.01172 |
| Sonnet 5 | $0.00030 | $0.00469 |
| Haiku 4.5 | $0.00015 | $0.00234 |
Grade A, and why
session-to-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 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session To Knowledge
Create one teachable article from one agent session. Reconstruct what was actually demonstrated; do not turn an assistant's claims into facts.
Resolve Lark Before Extraction
Run python3 <skill-root>/scripts/lark_publish.py status before extracting knowledge.
- If
lark-cliis absent or incompatible, continue with the local article and report that Lark publishing is unavailable. - If a compatible CLI is available but no global destination is configured, ask the user to choose
userorbotidentity and provide an existing Wiki Docx parent URL or token. Runconfigure --identity <user|bot> --parent <wiki-url-or-token>only after that choice. - For a missing user login, follow the installed
lark-sharedsplit-flow authorization with the Docs, Drive, and Wiki domains. A bot may use only a team Wiki it can access. Never runkeychain-downgradeautomatically. - Treat a successful configuration as standing consent to create future child documents below that parent. Require an explicit
--replaceand user confirmation to change it.
Do not block local knowledge capture when Lark setup or connectivity fails.
Choose The Source Path
- Use the current visible conversation when it is complete enough to inspect without loading any additional transcript.
- Use an explicit
source=<codex-task-id|transcript-path>when supplied. - Treat HTTP 413,
context_length_exceeded, a compacted session with missing evidence, or a transcript too large for one request as an oversized source. Read references/oversized-sessions.md and follow it completely. - If a rejected request was never persisted, ask the user to restate that request in the new session. Never reconstruct missing text.
A 413 response occurs before this skill runs. Do not promise to catch it inside the rejected session. Recover from a new, short session using the persisted task or transcript.
Resolve The Output
Resolve the project root in this order:
What ships with it
11 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.
- agents/openai.yaml 364 B
- assets/icon.png 690 B
- assets/icon.svg 559 B
- README.en.md 14 KB
- README.md 12 KB
- README.zh.md 12 KB
- references/oversized-sessions.md 11 KB
- scripts/lark_publish.py 32 KB runs code
- scripts/session_source.py 99 KB runs code
- tests/test_lark_publish.py 20 KB runs code
- tests/test_session_source.py 57 KB runs 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.
- 11d ago First seen · 161 lines · 150 tokens per session scan A 65d5291bb9fa
session-to-knowledge is a skill published in the GitHub repository tranfu-labs/tranfu-skills (2 stars, last pushed yesterday), licensed MIT. It adds 150 tokens to every session and 2,344 once invoked, about $0.0007 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.