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/alexknowshtml/smaug/process-bookmarksgit clone --depth 1 https://github.com/alexknowshtml/smaugWhat 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 | $0.00000 | $0.04380 |
| Opus 5 | $0.00000 | $0.02190 |
| Sonnet 5 | $0.00000 | $0.00876 |
| Haiku 4.5 | $0.00000 | $0.00438 |
Grade A, and why
process-bookmarks 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 2d 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 — 502 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/process-bookmarks
Process prepared Twitter bookmarks into a markdown archive with rich analysis and optional filing to a knowledge library.
Before You Start
CRITICAL: Use Edit Tool for bookmarks.md (DATA LOSS PREVENTION)
NEVER use the Write tool on bookmarks.md. The Write tool REPLACES the entire file, destroying all historical entries.
ALWAYS use the Edit tool to insert new entries into bookmarks.md. The Edit tool preserves existing content while making targeted insertions.
Write= Replace entire file (DANGEROUS - causes data loss)Edit= Insert/modify specific content (SAFE - preserves existing entries)
This applies to BOTH sequential processing AND the merge step in parallel processing.
Multi-Step Parallel Protocol (CRITICAL)
Create todo list IMMEDIATELY after reading bookmark count. This ensures final steps never get skipped.
Check parallelThreshold from config (default: 8). Use parallel processing only when bookmark count >= threshold. For smaller batches, sequential processing is faster due to subagent overhead.
node -e "console.log(require('./smaug.config.json').parallelThreshold ?? 8)"
For bookmarks below threshold (sequential):
TodoWrite({ todos: [
{content: "Read pending bookmarks", status: "pending", activeForm: "Reading pending bookmarks"},
{content: "Process bookmark 1", status: "pending", activeForm: "Processing bookmark 1"},
{content: "Process bookmark 2", status: "pending", activeForm: "Processing bookmark 2"},
{content: "Clean up pending file", status: "pending", activeForm: "Cleaning up pending file"},
{content: "Commit and push changes", status: "pending", activeForm: "Committing changes"},
{content: "Return summary", status: "pending", activeForm: "Returning summary"}
]})
For bookmarks at or above threshold (MUST use parallel subagents with batch files):
TodoWrite({ todos: [
{content: "Read pending bookmarks", status: "pending", activeForm: "Reading pending bookmarks"},
{content: "Spawn subagents to write batch files", status: "pending", activeForm: "Spawning subagents"},
{content: "Wait for all subagents to complete", status: "pending", activeForm: "Waiting for subagents"},
{content: "Merge batch files into bookmarks.md", status: "pending", activeForm: "Merging batch files"},
{content: "Clean up batch and pending files", status: "pending", activeForm: "Cleaning up files"},
{content: "Commit and push changes", status: "pending", activeForm: "Committing changes"},
{content: "Return summary", status: "pending", activeForm: "Returning summary"}
]})
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.
- 2d ago First seen · 502 lines · 0 tokens per session scan A 09b95811d41d
process-bookmarks is a command published in the GitHub repository alexknowshtml/smaug (850 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,380 tokens. 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 2026-08-30.
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.
constitution
Create or update the project constitution from interactive or provided principle inputs.
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.