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 commands/mdsakalu/agent-plugins/notesgit clone --depth 1 https://github.com/mdsakalu/agent-pluginsWhat 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 | $0.00005 | $0.00527 |
| Opus 5 | $0.00003 | $0.00264 |
| Sonnet 5 | $0.00001 | $0.00105 |
| Haiku 4.5 | $0.00001 | $0.00053 |
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.
What it actually says
Show or manage workspace notes.
Resolve the metarepo path by reading ~/.claude/workspace-config.json and expanding ~ to $HOME.
The user's request: $ARGUMENTS
Steps
- Read
~/.claude/workspace-config.jsonto get the metarepo path. Expand~to$HOME. - Determine which workspace's notes to show:
- If
<repo>/<workspace>specified, use it - If just
<workspace>, search across repos - If no argument, infer from cwd (match
*/repos/<repo>/<workspace>*) - If unable to determine, list workspaces and ask
- If
- Locate the notes directory at
<metarepo>/notes/<repo>/<workspace>/. - If the notes directory exists:
- Read and display
README.mdin full - Read and display
workspace.json(references, metadata) - List all other files in the notes directory with sizes and modification dates
- If the user asked about a specific file, read and display it
- Read and display
- Open the notes directory in MarkText:
Run this in the background (append~/Applications/marktext.app/Contents/MacOS/marktext <notes-dir>/&anddisown) so it doesn't block. - If the notes directory does not exist:
- Inform the user
- Offer to create it with README.md from
${CLAUDE_PLUGIN_ROOT}/templates/workspace-readme.md
- If the user asks to edit notes:
- Edit the requested file using the Edit tool
- Or create a new file in the notes directory
- Notes are also accessible via the
.notessymlink inside the workspace directory.
Important
- Always resolve metarepo from
~/.claude/workspace-config.json, never hardcode paths. - Notes are git-tracked at
<metarepo>/notes/<repo>/<workspace>/. - Notes persist even after workspace retirement — they are the historical record.
- The
.notessymlink in each workspace points to the notes directory. - workspace.json in the notes directory is the source of truth for metadata and references.
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 · 46 lines · 5 tokens per session scan A dfb0e15cc253
notes is a command published in the GitHub repository mdsakalu/agent-plugins (4 stars, last pushed 2mo ago), licensed MIT. It adds 5 tokens to every session and 527 once invoked, about $0.0000 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.