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/helpgit 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 | $0.00007 | $0.00330 |
| Opus 5 | $0.00003 | $0.00165 |
| Sonnet 5 | $0.00001 | $0.00066 |
| Haiku 4.5 | $0.00001 | $0.00033 |
Grade A, and why
help scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s "${SADDLE_BASE_URL:-http://127.0.0.1:1995}/health" What it actually says
You are helping the user verify the Saddle Claude Code plugin.
Requirements
saddle servemust be running in the project (defaulthttp://127.0.0.1:1995).- Optional env vars (shell or
.envnext to this plugin):SADDLE_BASE_URL,SADDLE_GROUP_ID,SADDLE_USER_ID. SetSADDLE_DISABLE=1to turn hooks off.
Check health
curl -s "${SADDLE_BASE_URL:-http://127.0.0.1:1995}/health"
Explain that this plugin stores conversation snippets in the local Saddle Memory API (POST /api/v1/memories) and retrieves them on submit (POST /api/v1/memories/search). For HTTP details see the Saddle repo docs/PLUGIN_HTTP.md.
Slash commands
/saddle:help— this help/saddle:modes— list mode names from the API/saddle:validate— validate thedefaultmode (requirespython -m saddleon PATH)/saddle:run— run the default pipeline (saddle run) viaPOST /api/v1/pipeline/run(requiressaddle serve); seecommands/run.md
Present a short status: if curl fails, tell the user to start python -m saddle serve from the project root.
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 · 28 lines · 7 tokens per session scan A 0b63f62cfc24
help is a command published in the GitHub repository deepelementlab/saddle (5 stars, last pushed 4mo ago), licensed MIT. It adds 7 tokens to every session and 330 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.