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/cabaynes/charles-claude-skillsnpx agentmods add skills/cabaynes/charles-claude-skills/takenotesWrote 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/cabaynes/charles-claude-skills/takenotes)<a href="https://agentmods.dev/skills/cabaynes/charles-claude-skills/takenotes"><img src="https://agentmods.dev/badge/skills/cabaynes/charles-claude-skills/takenotes/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/cabaynes/charles-claude-skills/takenotes"><img src="https://agentmods.dev/badge/skills/cabaynes/charles-claude-skills/takenotes.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 | $0.00149 | $0.07069 |
| Opus 5.5 | $0.00060 | $0.02828 |
| Sonnet 5.5 | $0.00030 | $0.01414 |
| Haiku 4.5 | $0.00015 | $0.00707 |
Grade A, and why
takenotes 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 — 495 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/takenotes — Harvest a session into durable memory
Write this session's durable knowledge somewhere it survives a /clear.
This is not a transcript dump. It is a harvest, a reconcile, and a routing decision.
The value of this skill over a plain "save that to memory" is Step 3. Anyone can append a new fact. Almost nobody goes back and checks whether what's already stored is still true. Do not skip it.
Step 0 — Scope gate (always first)
Decide which of these you're doing. Getting this wrong makes the skill annoying to use.
| Situation | Do this |
|---|---|
| One discrete fact ("remember I prefer tabs", "the API key rotates monthly") | Take the single-fact path below. Do not run Steps 2–5. |
| Session checkpoint — solved a problem, made a decision, finished a feature, asked to "save what we learned" | Full harvest. Continue to Step 1. |
A topic argument was passed (/takenotes auth flow) |
Full harvest, but scope Steps 2–4 to that topic only. |
Called from /putdown |
Full harvest. Continue to Step 1. |
| Nothing durable happened (pure Q&A, reading code, no decisions) | Say so plainly in one line and stop. Do not manufacture findings to look productive. But a session spent fighting tooling, access, or permissions is never "nothing durable" — that is Step 2a's whole subject, even when no code changed. |
Single-fact path
Skipping Steps 2–5 must not mean skipping the rules for writing a memory correctly. Do all of these, then stop:
- Locate the memory directory (Step 1a) — you still need to know where to write.
- Check for an existing memory on the topic (
ls "$MEMDIR/memory/") and update it rather than adding a second file that says nearly the same thing. - Decide scope. If the fact is about how the assistant should work or who you are, it applies to every project, not just this one — see Shared memories in Step 4a. If it's about this codebase, it's local.
- Add the one-line pointer to
MEMORY.md— a memory file with no index entry is a file nothing loads. - Say what you did, including the file path and whether it applies beyond this project.
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 Changed · +63 lines 9e4009472340
- 1mo ago Changed · +78 lines · +15 tokens per session c6d506acee93
- 1mo ago First seen · 354 lines · 134 tokens per session scan A 0e9352ba4162
takenotes is a skill published in the GitHub repository cabaynes/charles-claude-skills (1 stars, last pushed 1mo ago), licensed MIT. It adds 149 tokens to every session and 7,069 once invoked, about $0.0006 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
dream
A read-only review of project memories, notes, instructions, documents, and selected session records that produces a detailed report and a browser-viewable HTML report. It suggests ideas and insights but does not apply changes.
wake
A workflow for applying only the changes a user selected from a previously created dream report. It reads the saved choices and updates the specified memory or project notes.
metabot
Unified MetaBot CLI for personal Memory, Skill Hub, durable Agent Bus messaging, agent registry, Agent Teams, T5T, scheduling, and bridge runtime operations.
context-budget
Use when a coding session is burning context fast, output is drowning in noise, the model keeps forgetting earlier decisions, or the user asks to reduce tokens, stop the verbose narration, work in a huge repo, or make a long session survive. Covers what to read, what to summarize, what to write to disk, and when to…
session-handoff
Use when a working session is ending, the context window is nearly full, work needs to pass to a teammate or a fresh session, or the user says "hand this off", "write this up before we lose it", "I'm starting a new session", or "summarize where we are". Produces a handoff document that lets the next session resume…
conversation-archaeologist
Mine ALL past Claude conversations to build a living 'User Manual About You'. Extract writing style, business context, goals, preferences, and patterns. Make all other skills smarter with context.