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/deepelementlab/saddle/rungit clone --depth 1 https://github.com/deepelementlab/saddleWhat 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 | $0.00015 | $0.00337 |
| Opus 5 | $0.00008 | $0.00169 |
| Sonnet 5 | $0.00003 | $0.00067 |
| Haiku 4.5 | $0.00002 | $0.00034 |
Grade A, and why
run scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Runs saddle run through POST /api/v1/pipeline/run on SADDLE_BASE_URL (requires saddle serve).
Invoke
node "${CLAUDE_PLUGIN_ROOT}/commands/scripts/run-pipeline.js" "$ARGUMENTS"
Ways to pass input
- One string: the requirement text, with optional suffix
--mode fast(or another mode name). - Two tokens:
"requirement text"modeName(mode must be a single identifier-like token).
Examples for $ARGUMENTS:
Add login form --mode fastRefactor the APIfast(two arguments)
After the command: summarize whether the pipeline succeeded (ok / result.stages), highlight any stage failures, and suggest next steps. If the user sees HTTP errors, tell them to run python -m saddle serve from the project root and retry.
Fallback: the script may run python -m saddle run locally if the API is unreachable; set SADDLE_PYTHON to the correct interpreter if needed.
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 · 33 lines · 15 tokens per session scan A b06e20a869d4
run is a command published in the GitHub repository deepelementlab/saddle (5 stars, last pushed 4mo ago), licensed MIT. It adds 15 tokens to every session and 337 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
git
Git operations with intelligent commit messages and workflow optimization.
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.