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/darrylmorley/ollama-plugin-cc/setupgit clone --depth 1 https://github.com/darrylmorley/ollama-plugin-ccWhat 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 | $0.00020 | $0.00742 |
| Opus 5 | $0.00010 | $0.00371 |
| Sonnet 5 | $0.00004 | $0.00148 |
| Haiku 4.5 | $0.00002 | $0.00074 |
Grade A, and why
setup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run:
node "${CLAUDE_PLUGIN_ROOT}/scripts/ollama-companion.mjs" setup --json $ARGUMENTS
The setup command checks:
- Whether Node.js is available (required to run the companion script).
- Whether the
ollamabinary is installed (ollama --version). - Whether the Ollama server is reachable (
GET /api/tagsonOLLAMA_HOST, defaulthttp://127.0.0.1:11434). - Which models are installed locally; flags each one for tool-calling support.
- Whether a default model is configured (
OLLAMA_PLUGIN_DEFAULT_MODELor per-workspace config). - Whether the stop-time review gate is enabled.
If Ollama is not installed
Direct the user to install Ollama from https://ollama.com.
For macOS the recommended install is the desktop app or:
brew install ollama
If Ollama is installed but not running
Tell the user to start the server:
ollama serve
# or on macOS with Homebrew:
brew services start ollama
If no models are installed
Recommend pulling a model before using the plugin. Suggest based on use case:
- General review (baseline):
ollama pull llama3.1:8b - Code-heavy review:
ollama pull qwen2.5-coder:14b - Adversarial review:
ollama pull deepseek-coder-v2:16b - Stop-review gate only (minimal):
ollama pull qwen2.5:7b
Or let the command pull for the user:
/ollama:setup --pull llama3.1:8b
Optional flags
--pull <model>
Pulls the named model from the Ollama registry. Progress is streamed during the pull.
/ollama:setup --pull llama3.1:8b
/ollama:setup --pull qwen2.5-coder:14b
--default-model <name>
Writes the model name to the per-workspace plugin config. All commands fall back to this
when --model is not passed. OLLAMA_PLUGIN_DEFAULT_MODEL env var is also honoured as a
fallback if the config key is not set.
/ollama:setup --default-model llama3.1:8b
--enable-review-gate / --disable-review-gate
Toggles the stop-time review gate for the current workspace. When enabled, the plugin's
Stop hook runs an Ollama adversarial review after every Claude response and blocks the
stop if issues are found. Use with caution — it can create long Claude/Ollama loops.
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 · 94 lines · 20 tokens per session scan A 8275fd19418a
setup is a command published in the GitHub repository darrylmorley/ollama-plugin-cc (4 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 20 tokens to every session and 742 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.
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.