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 johnnywuj81/tokenknows --skill session_capturegit clone --depth 1 https://github.com/johnnywuj81/tokenknowsWrote 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/johnnywuj81/tokenknows/session_capture)<a href="https://agentmods.dev/skills/johnnywuj81/tokenknows/session_capture"><img src="https://agentmods.dev/badge/skills/johnnywuj81/tokenknows/session_capture/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/johnnywuj81/tokenknows/session_capture"><img src="https://agentmods.dev/badge/skills/johnnywuj81/tokenknows/session_capture.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 | $0.00091 | $0.01732 |
| Opus 5.5 | $0.00036 | $0.00693 |
| Sonnet 5.5 | $0.00018 | $0.00346 |
| Haiku 4.5 | $0.00009 | $0.00173 |
Grade A, and why
session_capture 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Capture · MUST Call After Every User Turn
This skill exists for ONE reason: persist the current conversation into TokenKnows so the user can later distill it into structured documents (weekly reports / ADRs / KG / tech designs / etc.).
If you do not call submit_session_events, the conversation is LOST from
TokenKnows. The user installed this plugin specifically to capture
everything. Skipping silently breaks the product.
Trigger Rules (MANDATORY · not "should" — MUST)
Invoke this skill after every meaningful user turn you answer:
| User did | Your action |
|---|---|
| Asked a question, you answered | ✅ Call submit_session_events with 2-3 events |
| Uploaded files / images, you interpreted them | ✅ 1 event summarizing files + your read |
| Made a decision after multi-turn discussion | ✅ Flush the discussion as 3-10 events before topic transition |
| Said only "ok" / "thanks" / "好的" / "嗯" | ❌ Skip (no semantic content) |
| Said "记一笔" / "保存" / "存档" | ✅ Explicit trigger, definitely call |
Topic transition: if user starts a new subject, flush the prior turns FIRST, then continue with the new topic.
Do NOT Skip Even When
These are common excuses LLMs use to skip — all wrong:
-
"User is near weekly usage limit, I should save tokens" — WRONG. One
submit_session_eventscall costs ~200-500 tokens. The conversation it captures costs 10×-100× more. Skipping wastes the user's weekly budget because they'll re-ask the same question later (no record). -
"This exchange feels small / casual" — WRONG. The user installed the plugin to capture EVERYTHING. Even a 2-turn casual chat may contribute to a later weekly_report. Always capture.
-
"I'm uncertain about title / tags / IDs" — WRONG. Backend tolerates rough input. Pick reasonable defaults:
title: 1-line summary of the turnexternal_id: leave unset (server auto-hashes)tags: 1-3 keywords from the conversationsource_ref: any stable session identifier
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 · 161 lines · 91 tokens per session scan A f00bf1bbf539
session_capture is a skill published in the GitHub repository johnnywuj81/tokenknows (4 stars, last pushed 1mo ago), licensed MIT. It adds 91 tokens to every session and 1,732 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
ex-example_xiaoming
An example relationship-memory and persona package for an AI agent, written in Chinese. It contains placeholder details and explicitly does not describe a real person.
create-ex
A skill for turning information about a former partner into an AI skill, using imported chat histories, photos, and social-media posts to create relationship memories and a persona.
kiro-steering-custom
Create custom steering documents for specialized project contexts.
memory-import
Bulk-import an external knowledge base into Prismer memory via the three-layer import pipeline (07 §3.1). Use when the user asks to import/migrate documents, a knowledge base, or notes into workspace memory. Layer 1 lands raw documents (zero LLM, instantly searchable); Layer 2 is YOUR distillation work — you read the…
identity-snapshot
Generate a living profile of the user's working patterns, decision tendencies and quality preferences from their Dex data. Use when the user says 'what are my patterns', 'how do I work', or during week-review. Also use proactively when the model (older than 7 days) is stale. Not for planning a week; use week-plan.
daily-journal
A passive daily work journal that Claude keeps FOR you so you never have to write it yourself. Append short entries after meaningful work (what was done, what you focused on, artifacts touched) to 01-daily/journal/YYYY-MM-DD.md. Run a guided reflection at night or in the morning. Use when you run /daily-journal, say…