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/mischacoster/claude-code-notes/notesnpx skills add mischacoster/Claude-Code-Notes --skill notesgit clone --depth 1 https://github.com/mischacoster/Claude-Code-NotesWhat 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 | $0.00033 | $0.01634 |
| Opus 5 | $0.00016 | $0.00817 |
| Sonnet 5 | $0.00007 | $0.00327 |
| Haiku 4.5 | $0.00003 | $0.00163 |
Grade A, and why
notes 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 yesterday.
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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a quick-capture assistant. Behave based on whether ARGUMENTS is provided.
First, check if ARGUMENTS starts with -r (research mode flag) or equals exactly -r. If so, strip the flag from ARGUMENTS and use MODE A-RESEARCH. If ARGUMENTS is -r with no idea after it, output "Please provide an idea: /notes -r [idea]" and STOP. If ARGUMENTS is provided without -r, use MODE A-CAPTURE. If no ARGUMENTS at all, use MODE B.
MODE A-CAPTURE: QUICK SAVE (default)
No bypass permissions needed. Uses Read/Write tools instead of Bash.
Step 1: Read NOTES.md
Use the Read tool to read NOTES.md. If it doesn't exist, that's fine — we'll create it.
Step 2: Write the note entry
Generate a timestamp in YYYY-MM-DD HH:MM format.
If NOTES.md didn't exist, use the Write tool to create it with:
# 💡 Ideas & Notes
Capture notes mid-session. Each note gets a research brief in notes/.
---
**[TIMESTAMP]** — ARGUMENTS
- Status: 📝 Captured
---
If NOTES.md already existed, use the Write tool to rewrite the full file with the new entry appended at the end:
---
**[TIMESTAMP]** — ARGUMENTS
- Status: 📝 Captured
---
Step 3: Session-start reminder
If CLAUDE.md exists and does not already contain "NOTES.md", use the Edit tool to append:
## Session Start
If NOTES.md exists and has 📝 Captured, 🆕 New, or 🔍 Analyzed entries, briefly mention the count.
Step 4: Output (exactly this, nothing more)
💾 Saved to NOTES.md
↩️ Resuming...
If CLAUDE.md was updated in Step 3, append: 📌 Added session-start reminder to CLAUDE.md
STOP. Do not elaborate. Resume the previous task immediately.
MODE A-RESEARCH: CAPTURE + BACKGROUND RESEARCH (-r flag)
Requires bypass permissions for the background research agent to write files.
Step 1: Bash (file I/O only, no spawning)
[ ! -f NOTES.md ] && IS_FIRST=true || IS_FIRST=false
if [ "$IS_FIRST" = "true" ]; then
printf '# 💡 Ideas & Notes\n\nCapture notes mid-session. Each note gets a research brief in notes/.\n\n' > NOTES.md
fi
mkdir -p notes
SLUG=$(printf '%s' "$ARGUMENTS" | tr '[:upper:]' '[:lower:]' | sed 's/[^a-z0-9]/-/g; s/--*/-/g' | cut -c1-50)
TIMESTAMP=$(date '+%Y-%m-%d %H:%M')
DATE_SLUG=$(date '+%Y%m%d-%H%M')
BRIEF_FILE="notes/${DATE_SLUG}-${SLUG}.md"
printf '\n---\n**[%s]** — %s\n- Status: 🆕 New\n- Brief: [%s](%s)\n---\n' \
"$TIMESTAMP" "$ARGUMENTS" "$BRIEF_FILE" "$BRIEF_FILE" >> NOTES.md
if [ -f CLAUDE.md ] && ! grep -q "NOTES.md" CLAUDE.md; then
printf '\n## Session Start\nIf NOTES.md exists and has 📝 Captured, 🆕 New, or 🔍 Analyzed entries, briefly mention the count.\n' >> CLAUDE.md
fi
printf 'BRIEF_FILE=%s\nTIMESTAMP=%s\nIS_FIRST=%s\n' "$BRIEF_FILE" "$TIMESTAMP" "$IS_FIRST"
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.
- yesterday First seen · 194 lines · 33 tokens per session scan A f77dd8c84e16
notes is a skill published in the GitHub repository mischacoster/Claude-Code-Notes (5 stars, last pushed 5mo ago), licensed MIT. It adds 33 tokens to every session and 1,634 once invoked, about $0.0002 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…