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/bundl-ai/bundl-cli/taskgit clone --depth 1 https://github.com/Bundl-AI/bundl-cliWhat 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 | $0.00229 |
| Opus 5 | $0.00000 | $0.00114 |
| Sonnet 5 | $0.00000 | $0.00046 |
| Haiku 4.5 | $0.00000 | $0.00023 |
Grade A, and why
task 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.
This is a copy
88% identical to icp — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Path rules — read first
- Company files: workspace/company/[name].md NEVER workspace/[name].md (wrong) ALWAYS workspace/company/[name].md (correct)
- Memory files: workspace/memory/[name].md
- Artifact files: workspace/artifacts/[type]/[name].md
- Commands files: workspace/commands/[name].md
- Use >> to append when the file already has real content. If the file still only has the stub "# Title" and "Not yet defined.", use > to overwrite with the title, a blank line, and your content (do not leave the stub). Exception: /save always uses > for new artifact files.
- Maximum 2 tool calls for /note: call 1 cat target file, call 2 echo >> append (or echo > if file is still stub-only). Do not mkdir, do not check if file exists. Files are guaranteed to exist.
/task
What it does
Queues a task for the agent. Execute it (load skills if needed, run_bash). Confirm when done.
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 · 17 lines · 0 tokens per session scan A 5ba77a629a21
task is a command published in the GitHub repository Bundl-AI/bundl-cli (7 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 229 tokens. A static security scan graded it A with 0 findings. It is 88% identical to icp, differing in 4 lines, and is treated as a copy.
Other commands, from other repositories
speckit.model-selector
Select the best OpenRouter model for each SpecKit workflow step and write model metadata into each command file.
prepare-dataset
Analyse a raw data file (CSV, JSON, JSONL, TSV, Parquet) and generate a complete Python script scripts/dataset/ .py that inherits from BaseDatasetPreparer and transforms the file into a JSONL dataset ready for fine-tuning with Unsloth.
speckit.polish
Polish and complete speckit workflow — quality gate, docs, changelog, MR.
documentation
Strictly follow the project constitution.
next-sprint-design
You are helping a DevOps engineer prepare a sprint kickoff message for Slack.
commit-and-create-mr
Commit and create MR on Gitlab.