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/lhohan/claude-code-plugins/bsky-threadgit clone --depth 1 https://github.com/lhohan/claude-code-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 | $0.00012 | $0.00678 |
| Opus 5 | $0.00006 | $0.00339 |
| Sonnet 5 | $0.00002 | $0.00136 |
| Haiku 4.5 | $0.00001 | $0.00068 |
Grade A, and why
bsky-thread 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are tasked with splitting text into Bluesky-compatible thread messages. Bluesky has a 300 character limit per post.
The user input below is either a file path or raw text:
{{prompt}}
Task Instructions
-
Detect Input Type:
- If input starts with
@, it's a Claude Code file reference - convert to absolute path and read it - Check if the input is a file path (absolute paths or paths ending with common extensions like .txt, .md, etc.)
- If it looks like a file path, use the Read tool to load the file content
- If a file path is provided but doesn't have an extension (like LICENSE), still try to read it as a file
- Otherwise, treat the entire input as the text to split
- If input starts with
-
Split Algorithm:
- Target: 300 characters per message (use ~280-290 character soft limit to leave room for thread numbering like "[1/5] ")
- Split at natural boundaries in this order of preference:
- Paragraph breaks (empty lines)
- Sentence endings (periods, question marks, exclamation marks)
- Clause boundaries (commas, semicolons)
- Word boundaries (last resort)
- Never split mid-word or mid-sentence unless absolutely necessary
- Preserve leading/trailing whitespace handling for readability
-
Output Format:
- Start with a header showing total message count:
=� This will create X messages for your Bluesky thread: - Separate each message clearly with a visual divider
- For each message, show:
- Message label:
[N/TOTAL] - Character count:
(NNN chars)- count includes the "[N/TOTAL] " prefix - The actual message text with the
[N/TOTAL]prefix included
- Message label:
- Include empty lines between messages for readability
- Start with a header showing total message count:
-
Suggested Improvements (only if improvements are actually applicable):
- After all messages, add a "=� Suggested improvements:" section
- Suggest alternative thread break points that improve narrative flow or pacing
- Propose minor clarity edits that maintain tone and content (grammar, awkward phrasing, etc.)
- Format:
- [Message N] Suggestion hereor- [Overall] Suggestion here - Only include suggestions that genuinely improve the content
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 · 63 lines · 12 tokens per session scan A f6bcefef8983
bsky-thread is a command published in the GitHub repository lhohan/claude-code-plugins (2 stars, last pushed 9mo ago), licensed MIT. It adds 12 tokens to every session and 678 once invoked, about $0.0001 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.