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/steipete/summarize/refresh-freegit clone --depth 1 https://github.com/steipete/summarizeWhat 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 | $0.00727 |
| Opus 5 | $0.00000 | $0.00364 |
| Sonnet 5 | $0.00000 | $0.00145 |
| Haiku 4.5 | $0.00000 | $0.00073 |
Grade A, and why
refresh-free 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
summarize refresh-free
summarize refresh-free [--runs 2] [--smart 3] [--min-params 27b]
[--max-age-days 180] [--set-default] [--verbose]
Probes OpenRouter's catalog for :free models, runs them on a small benchmark, and writes the working ones to models.free in ~/.summarize/config.json. Useful when you want to use --model free without picking a specific OpenRouter slug.
Needs OPENROUTER_API_KEY in the environment.
What it does
- Pulls the OpenRouter model catalog.
- Filters to models tagged
:freethat meet--min-paramsand--max-age-days. - Runs each candidate
--runstimes against a sanity prompt; ranks by--smartheuristics (latency, completion length, refusal rate). - Writes the survivors to
models.freein~/.summarize/config.json. - With
--set-default, also sets top-levelmodeltofree.
After the run, summarize "https://example.com" --model free rotates through the saved list until one succeeds.
Flags
--runs <n>
: How many times to probe each candidate. Default 2.
--smart <n>
: How many top candidates to keep. Default 3.
--min-params <size>
: Minimum parameter count. Accepts 7b, 27b, 70b, etc. Default 27b.
--max-age-days <n>
: Reject models older than N days based on OpenRouter's metadata. Default 180.
--set-default
: Also set model: "free" at the top level of ~/.summarize/config.json.
--verbose
: Per-candidate progress, timings, and rejection reasons on stderr.
Examples
# Quick refresh; keep the best 3 free models ≥27B, ≤180d old.
summarize refresh-free
# Looser filter — accept smaller / older models.
summarize refresh-free --min-params 7b --max-age-days 365
# Refresh and also set the default model.
summarize refresh-free --set-default
# Verbose ranking output for debugging.
summarize refresh-free --runs 3 --smart 5 --verbose
Output
~/.summarize/config.json is updated in place. The relevant section ends up looking like:
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 · 84 lines · 0 tokens per session scan A b1ce11735cd1
refresh-free is a command published in the GitHub repository steipete/summarize (6,588 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 727 tokens. 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 2026-08-30.
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.