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 ohong/agent-skills --skill take-notesgit clone --depth 1 https://github.com/ohong/agent-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/ohong/agent-skills/take-notes)<a href="https://agentmods.dev/skills/ohong/agent-skills/take-notes"><img src="https://agentmods.dev/badge/skills/ohong/agent-skills/take-notes/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/ohong/agent-skills/take-notes"><img src="https://agentmods.dev/badge/skills/ohong/agent-skills/take-notes.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 | $0.00036 | $0.00830 |
| Opus 5.5 | $0.00014 | $0.00332 |
| Sonnet 5.5 | $0.00007 | $0.00166 |
| Haiku 4.5 | $0.00004 | $0.00083 |
Grade A, and why
take-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 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Take notes
Save useful material that exists only in the current session. Keep learnings, takeaways, references, and generated prompts to run next or later.
Exclude decisions, status, completed-work updates, blockers, and material already recorded in the project. Decisions belong in DECISIONS.md; this skill does not edit it. Do not archive tasks or commit changes.
Select the material
Read the available conversation and identify what is worth keeping. Check relevant project files and existing notes for duplication. Keep this check narrow; do not audit the repository.
If history is truncated, use current-session retrieval when available. Never read unrelated sessions. State any history gap in the response. If you save new material, also add a short factual coverage notice to the note. Do not claim to have read the full transcript unless you did.
Write original prose in concise, ASD-STE100-style simple English. Use common words, short complete sentences, and active voice. Do not claim formal compliance. Preserve useful links and references. Copy generated prompts in full, verbatim, including all constraints. Put prompts in fenced blocks; use longer fences if a prompt contains fences. Do not shorten prompts to meet the writing style.
Save the material as recorded. Do not execute saved prompts, refresh old research, or check work status.
Use headings only when they help. Do not add empty sections or pad the note. If nothing useful is new, report that and do not save.
Locate and save
Use scripts/take_notes.py for file identity and writes. Run it from the current project directory.
The helper uses CODEX_THREAD_ID. If it is unavailable, supply --session-id only from verified current-session context. Never infer an ID from a title. If no stable ID is available, ask for it before saving.
Git projects save in the main checkout's notes/, including when this session runs in a linked worktree. For a non-Git project, identify its root from the task or project context and pass --project-root /absolute/path. Do not assume an arbitrary working directory is the project root. Without Git or a known project root, notes go in ~/dev/notes. Use --projectless to force this fallback. A broken Git location is an error, not a reason to choose another destination.
What ships with it
3 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.
- 1mo ago First seen · 47 lines · 36 tokens per session scan A 8740c776d4d1
take-notes is a skill published in the GitHub repository ohong/agent-skills (4 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 830 once invoked, about $0.0001 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 2026-09-15.
Other skills, from other repositories
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
forget
Remove a personal fact, preference, relationship detail, topic, or prior event from Muse's active memory and stop existing copies or automations from bringing it back. Use for explicit requests such as 'forget that', 'don't remember this about me', or 'remove that from your memory'. Do not use when 'forget it' merely…
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.